{"schema_version":7,"identifier":"artificial-analysis:humanitys-last-exam","retrieval_mode":"direct","data":{"source":"local","citation":{"apa":"Wu, K., Zhang, W., Zhou, J., Han, P., Shang, E., Wang, J., Wang, J., Xu, W., Lu, S., Li, Y., Mizrahi Celekli, R., Ravshanov, L., Bian, Y., Han, X., & Shi, L. (2026). Benchmark Radar: A living database and search engine for AI benchmarks and evaluation. arXiv:2609.11115. https://arxiv.org/abs/2609.11115","bibtex":"@misc{wu2026benchmarkradarlivingdatabase,\n      title={Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation},\n      author={Koutian Wu and Wenjun Zhang and Junjie Zhou and Pengqian Han and Ergan Shang and Jiayu Wang and Junkai Wang and Wanghan Xu and Songyuanyi Lu and Yixuan Li and Rudy {Mizrahi Celekli} and Lazizbek Ravshanov and Yaoliang Bian and Xudong Han and Lin Shi},\n      year={2026},\n      eprint={2609.11115},\n      archivePrefix={arXiv},\n      primaryClass={cs.AI},\n      url={https://arxiv.org/abs/2609.11115},\n}","latex":"\\cite{wu2026benchmarkradarlivingdatabase}","arxiv_id":"2609.11115","url":"https://arxiv.org/abs/2609.11115","formats_url":"https://benchmark-radar.org/#cite"},"data_version":"data-3f9e38f5eb1d0076","catalog_path":"site/data/benchmark-index.json","catalog_schema_version":1,"catalog_count":3772,"shard_path":"site/data/benchmarks/artificial-analysis-humanitys-last-exam.json"},"required_citations":[{"id":"benchmark-radar","key":"wu2026benchmarkradarlivingdatabase","reason":"You used Benchmark Radar for this material. Please cite it; we can add it for you.","bibtex":"@misc{wu2026benchmarkradarlivingdatabase,\n      title={Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation},\n      author={Koutian Wu and Wenjun Zhang and Junjie Zhou and Pengqian Han and Ergan Shang and Jiayu Wang and Junkai Wang and Wanghan Xu and Songyuanyi Lu and Yixuan Li and Rudy {Mizrahi Celekli} and Lazizbek Ravshanov and Yaoliang Bian and Xudong Han and Lin Shi},\n      year={2026},\n      eprint={2609.11115},\n      archivePrefix={arXiv},\n      primaryClass={cs.AI},\n      url={https://arxiv.org/abs/2609.11115},\n}"}],"benchmark":{"record":{"aliases":[],"artifacts":[],"categories":["intelligence-index","reasoning","knowledge"],"description":{"en":"Reasoning & knowledge"},"documents":[{"document_type":"registry_page","id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","title":"Humanity’s Last Exam"}],"editorial_guide":{"id":"artificial-analysis-humanitys-last-exam","record_keys":["artificial-analysis:humanitys-last-exam"],"reviewed_at":"2026-10-29","scope":{"en":"The Artificial Analysis results collected on 25 August 2026. Original HLE publications and current methodology are linked for context; later revisions do not establish each saved run’s setup.","zh":"对应 2026 年 8 月 25 日采集的 Artificial Analysis 成绩。原始 HLE 发布资料与现行方法文档用于解释评测，后续修订不能证明每条历史成绩的运行配置。"},"sections":[{"id":"task","source_ids":["project","paper","evaluation"],"text":{"en":"Developed by the Center for AI Safety and Scale AI with expert contributors, HLE combines multiple-choice and short-answer questions across mathematics, humanities and the natural sciences. The original project links its paper, dataset and evaluation code. Artificial Analysis conducts its own evaluations; its results remain distinct from the original authors’ leaderboard.","zh":"HLE 由 Center for AI Safety、Scale AI 与专家贡献者共同开发，包含数学、人文与自然科学领域的选择题和简答题。原始项目提供论文、数据集与评测代码。Artificial Analysis 独立运行评测，本页成绩与原作者榜单分别保留。"},"title":{"en":"Expert questions across academic subjects","zh":"跨学科的专家级问题"}},{"id":"dates","source_ids":["announcement","paper","saved-record"],"text":{"en":"The public benchmark announcement is dated 23 January 2025; the first arXiv submission is dated 24 January. This record was collected on 25 August 2026. Dates beside individual results are model announcement dates, labelled as a model release proxy, not the dates those evaluations were run. The captured source does not provide per-run dates.","zh":"评测公开发布公告的日期是 2025 年 1 月 23 日，arXiv 首次提交日期是 1 月 24 日。本条记录采集于 2026 年 8 月 25 日。逐条成绩旁的日期是模型公布日期，页面将其标为模型发布日期代理，并非该次评测的运行日期；采集来源未提供逐次运行日期。"},"title":{"en":"Release, collection and model dates","zh":"发布日期、采集日期与模型日期"}},{"id":"configurations","source_ids":["saved-record","evaluation"],"text":{"en":"Model names retain the source’s version, reasoning-effort and fallback labels where supplied. Rows also retain the source’s model identity. A display name does not establish an immutable provider API revision; that revision was not supplied in the captured table. Units and per-run protocols that were not recorded remain unknown, and the original numeric values are preserved.","zh":"模型名称保留来源提供的版本、推理强度及回退配置，数据也保留来源的模型标识。显示名称不能证明不可变的 API 修订版本，采集表中没有提供这项信息。未记录的单位与逐次运行协议仍标为未知，原始数值保持不变。"},"title":{"en":"Keep the model configuration attached","zh":"保留模型的具体配置"}},{"id":"methodology","source_ids":["methodology","saved-record"],"text":{"en":"The methodology reviewed on 29 October is v5.0 and describes HLE as 2,158 text-only questions from the May 2025 revision, scored with pass@1. It treats HLE-Diamond separately. This provides context, not verified historical settings for every saved row. Do not substitute today’s grader, dataset revision or leaderboard values for the captured results.","zh":"10 月 29 日查阅的现行方法为 v5.0，将 HLE 描述为 2025 年 5 月修订版中的 2,158 道纯文本题，采用 pass@1 计分，并单独列出 HLE-Diamond。这些内容用于帮助理解评测，不能证明每条历史成绩的配置，也不能用今天的评分模型、题集修订或榜单数值替换已采集结果。"},"title":{"en":"Read current methodology with the snapshot date","zh":"结合快照日期阅读现行方法"}}],"sources":[{"id":"project","title":"Humanity’s Last Exam · original project","url":"https://lastexam.ai/"},{"id":"paper","title":"Humanity’s Last Exam · paper and version history","url":"https://arxiv.org/abs/2501.14249"},{"id":"announcement","title":"Scale AI and CAIS · public announcement dated 23 January 2025","url":"https://scale.com/blog/humanitys-last-exam-results"},{"id":"evaluation","title":"Artificial Analysis · Humanity’s Last Exam evaluation","url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam"},{"id":"methodology","title":"Artificial Analysis · current methodology, reviewed 29 October 2026","url":"https://artificialanalysis.ai/methodology/intelligence-benchmarking"},{"id":"saved-record","title":"AI Benchmark Radar · saved record, collection timestamp and row date basis","url":"https://aibenchmarkradar.com/api/v1/benchmarks/artificial-analysis-humanitys-last-exam"}],"summary":{"en":"Humanity’s Last Exam tests expert-level academic knowledge and reasoning. This page preserves Artificial Analysis’s collected model results, with the original benchmark and date meanings explained below.","zh":"Humanity’s Last Exam 考查专家级学术知识与推理。本页保留采集自 Artificial Analysis 的模型成绩，并说明原始评测来源与各类日期的含义。"},"title":"Humanity’s Last Exam · Artificial Analysis"},"evidence_summary":{"document_count":1,"model_count":577,"model_count_basis":"source_model_id"},"key":"artificial-analysis:humanitys-last-exam","modality":null,"name":"Humanity’s Last Exam","openness":{"code_license":null,"data_license":null,"evidence":[],"status":"unknown"},"provenance":{"crawl_bundle":"artificial_analysis_2026-08-25","crawled_at":"2026-08-25T10:41:06Z","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam"},"publication":{"evidence":[{"note":"Artificial Analysis names Humanity’s Last Exam, identifies its independent evaluation and links arXiv 2501.14249, the cais/hle dataset and the centerforaisafety/hle repository. This establishes the exact-record publication association without transferring other scores.","url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam"},{"note":"The original HLE project links the same paper, dataset and repository and identifies the Center for AI Safety and Scale AI organizing team. Later revisions remain separate from the captured Artificial Analysis results.","url":"https://lastexam.ai/"}],"id":"artificial-analysis-humanitys-last-exam-original","links":[{"kind":"website","title":"Humanity’s Last Exam · original project","url":"https://lastexam.ai/"},{"kind":"paper","title":"Humanity’s Last Exam · original paper and version history","url":"https://arxiv.org/abs/2501.14249"},{"kind":"dataset","title":"Humanity’s Last Exam · official dataset","url":"https://huggingface.co/datasets/cais/hle"},{"kind":"repo","title":"Humanity’s Last Exam · official evaluation repository","url":"https://github.com/centerforaisafety/hle"}],"record_keys":["artificial-analysis:humanitys-last-exam"],"reviewed_at":"2026-10-29","scope":{"en":"Original Humanity’s Last Exam publications for this Artificial Analysis source record. Scores remain the separately collected Artificial Analysis snapshot from 25 August 2026; later publication and dataset revisions do not establish the setup of every saved evaluation.","zh":"本条 Artificial Analysis 记录对应的原始 Humanity’s Last Exam 发布资料。成绩仍为独立采集的 2026 年 8 月 25 日 Artificial Analysis 快照；论文与数据集的后续修订不能证明每条历史评测的具体配置。"}},"publisher":null,"released":"2025-01-23","released_reference":{"basis":"release_announcement","note":"Scale and CAIS announce the public HLE benchmark and results on January 23, before the January 24 arXiv submission. GPT-4 model releases in 2023 do not date HLE.","source_key":"artificial-analysis:humanitys-last-exam","source_url":"https://scale.com/blog/humanitys-last-exam-results"},"schema_version":1,"sizes":[],"slug":"artificial-analysis-humanitys-last-exam","source":"artificial_analysis","source_benchmark_id":"humanitys-last-exam","topics":["reasoning-math"]},"schema_version":1,"scores_by_source":{"artificial_analysis":{"rows":[{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"cd55210d-358e-4df1-ba9c-9acb5f186cc9","model_name":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)","obs_id":"artificial_analysis:humanitys-last-exam:cd55210d-358e-4df1-ba9c-9acb5f186cc9","organization":"Anthropic","rank_in_source_response":1,"raw_value":"0.554680259499537","reported_by":"third_party","reported_date":"2026-06-09","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.554680259499537,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"b8fc61f7-5e9a-49e6-8547-6ac56db24627","model_name":"Claude Opus 5 (Adaptive Reasoning, Max Effort)","obs_id":"artificial_analysis:humanitys-last-exam:b8fc61f7-5e9a-49e6-8547-6ac56db24627","organization":"Anthropic","rank_in_source_response":2,"raw_value":"0.548656163113994","reported_by":"third_party","reported_date":"2026-07-24","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.548656163113994,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"1305c921-7aaa-4d6d-99b5-99b3acf15e19","model_name":"Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)","obs_id":"artificial_analysis:humanitys-last-exam:1305c921-7aaa-4d6d-99b5-99b3acf15e19","organization":"Anthropic","rank_in_source_response":3,"raw_value":"0.544022242817424","reported_by":"third_party","reported_date":"2026-07-24","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.544022242817424,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"712be54a-77ae-41b2-9a58-21181479d6ee","model_name":"Claude Opus 5 (Adaptive Reasoning, High Effort)","obs_id":"artificial_analysis:humanitys-last-exam:712be54a-77ae-41b2-9a58-21181479d6ee","organization":"Anthropic","rank_in_source_response":4,"raw_value":"0.528266913809083","reported_by":"third_party","reported_date":"2026-07-24","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.528266913809083,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"ff51be8f-e362-4a7e-9043-687ba15de207","model_name":"Claude Opus 5 (Adaptive Reasoning, Medium Effort)","obs_id":"artificial_analysis:humanitys-last-exam:ff51be8f-e362-4a7e-9043-687ba15de207","organization":"Anthropic","rank_in_source_response":5,"raw_value":"0.512974976830398","reported_by":"third_party","reported_date":"2026-07-24","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.512974976830398,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"d93edfe8-bf35-49ad-b56e-b18116142a1c","model_name":"GPT-5.6 Sol (max)","obs_id":"artificial_analysis:humanitys-last-exam:d93edfe8-bf35-49ad-b56e-b18116142a1c","organization":"OpenAI","rank_in_source_response":6,"raw_value":"0.494902687673772","reported_by":"third_party","reported_date":"2026-07-09","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.494902687673772,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"992b7b84-5069-4c6a-9295-834252553d50","model_name":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort)","obs_id":"artificial_analysis:humanitys-last-exam:992b7b84-5069-4c6a-9295-834252553d50","organization":"Anthropic","rank_in_source_response":7,"raw_value":"0.486561631139944","reported_by":"third_party","reported_date":"2026-05-28","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.486561631139944,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"b2331108-72ed-415a-82d1-188633875bbc","model_name":"Gemini 3.7 Flash (high)","obs_id":"artificial_analysis:humanitys-last-exam:b2331108-72ed-415a-82d1-188633875bbc","organization":"Google","rank_in_source_response":8,"raw_value":"0.478683966635774","reported_by":"third_party","reported_date":"2026-08-13","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.478683966635774,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"d998db47-9b67-4727-a2bb-2e1261020ac0","model_name":"GPT-5.6 Sol (xhigh)","obs_id":"artificial_analysis:humanitys-last-exam:d998db47-9b67-4727-a2bb-2e1261020ac0","organization":"OpenAI","rank_in_source_response":9,"raw_value":"0.473123262279889","reported_by":"third_party","reported_date":"2026-07-09","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.473123262279889,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"bbd93ebe-80da-4594-bb19-61e69d0331df","model_name":"Gemini 3.1 Pro Preview","obs_id":"artificial_analysis:humanitys-last-exam:bbd93ebe-80da-4594-bb19-61e69d0331df","organization":"Google","rank_in_source_response":10,"raw_value":"0.470342910101946","reported_by":"third_party","reported_date":"2026-02-19","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.470342910101946,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"f7d2fc3e-1f7b-405f-818c-07952a4af78f","model_name":"Kimi K3 (max)","obs_id":"artificial_analysis:humanitys-last-exam:f7d2fc3e-1f7b-405f-818c-07952a4af78f","organization":"Moonshot AI","rank_in_source_response":11,"raw_value":"0.468952734012975","reported_by":"third_party","reported_date":"2026-07-16","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.468952734012975,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"d61493e2-43ff-460c-9054-eaf6ba317360","model_name":"Muse Spark 1.1 (xhigh)","obs_id":"artificial_analysis:humanitys-last-exam:d61493e2-43ff-460c-9054-eaf6ba317360","organization":"Meta","rank_in_source_response":12,"raw_value":"0.462001853568119","reported_by":"third_party","reported_date":"2026-07-09","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.462001853568119,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"8afc250d-b538-45a2-812a-4605f4ffd87e","model_name":"GPT-5.6 Sol (high)","obs_id":"artificial_analysis:humanitys-last-exam:8afc250d-b538-45a2-812a-4605f4ffd87e","organization":"OpenAI","rank_in_source_response":13,"raw_value":"0.46014828544949","reported_by":"third_party","reported_date":"2026-07-09","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.46014828544949,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"1f054429-397e-4fdb-9e71-67bc92c1735e","model_name":"GPT-5.5 (xhigh)","obs_id":"artificial_analysis:humanitys-last-exam:1f054429-397e-4fdb-9e71-67bc92c1735e","organization":"OpenAI","rank_in_source_response":14,"raw_value":"0.457831325301205","reported_by":"third_party","reported_date":"2026-04-23","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.457831325301205,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"04ee6719-0327-463b-a1a1-70a6a78254f9","model_name":"Muse Spark 1.2 (xhigh)","obs_id":"artificial_analysis:humanitys-last-exam:04ee6719-0327-463b-a1a1-70a6a78254f9","organization":"Meta","rank_in_source_response":15,"raw_value":"0.454587581093605","reported_by":"third_party","reported_date":"2026-08-05","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.454587581093605,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"b13c1257-d746-4027-8fc8-4892dc14701c","model_name":"GPT-5.5 (high)","obs_id":"artificial_analysis:humanitys-last-exam:b13c1257-d746-4027-8fc8-4892dc14701c","organization":"OpenAI","rank_in_source_response":16,"raw_value":"0.450417052826691","reported_by":"third_party","reported_date":"2026-04-23","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.450417052826691,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"d6f43d0a-e8c4-447c-9ff7-5cf0a9d59aa3","model_name":"Grok 4.6 (xhigh)","obs_id":"artificial_analysis:humanitys-last-exam:d6f43d0a-e8c4-447c-9ff7-5cf0a9d59aa3","organization":"xAI","rank_in_source_response":17,"raw_value":"0.440685820203893","reported_by":"third_party","reported_date":"2026-08-12","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.440685820203893,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"a89c4b28-2d8c-456e-88ea-255fb51fd2b6","model_name":"GPT-5.4 (xhigh)","obs_id":"artificial_analysis:humanitys-last-exam:a89c4b28-2d8c-456e-88ea-255fb51fd2b6","organization":"OpenAI","rank_in_source_response":18,"raw_value":"0.437442075996293","reported_by":"third_party","reported_date":"2026-03-05","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.437442075996293,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"20928ba9-3a3f-415f-9519-b84ff64ecf34","model_name":"Claude Opus 5 (Adaptive Reasoning, Low Effort)","obs_id":"artificial_analysis:humanitys-last-exam:20928ba9-3a3f-415f-9519-b84ff64ecf34","organization":"Anthropic","rank_in_source_response":19,"raw_value":"0.434198331788693","reported_by":"third_party","reported_date":"2026-07-24","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.434198331788693,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"5e5b4ce7-bc54-47b2-b911-21b9cad8394c","model_name":"Qwen3.8 Max","obs_id":"artificial_analysis:humanitys-last-exam:5e5b4ce7-bc54-47b2-b911-21b9cad8394c","organization":"Qwen","rank_in_source_response":20,"raw_value":"0.430491195551437","reported_by":"third_party","reported_date":"2026-08-03","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.430491195551437,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"bcf8db0a-3bb6-4d82-9516-0f57370c85a6","model_name":"GPT-5.6 Terra (max)","obs_id":"artificial_analysis:humanitys-last-exam:bcf8db0a-3bb6-4d82-9516-0f57370c85a6","organization":"OpenAI","rank_in_source_response":21,"raw_value":"0.429101019462465","reported_by":"third_party","reported_date":"2026-07-09","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.429101019462465,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"c8adc5cf-fd5a-407b-af51-dc3bede3e49c","model_name":"Grok 4.6 (high)","obs_id":"artificial_analysis:humanitys-last-exam:c8adc5cf-fd5a-407b-af51-dc3bede3e49c","organization":"xAI","rank_in_source_response":21,"raw_value":"0.429101019462465","reported_by":"third_party","reported_date":"2026-08-12","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.429101019462465,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"0097ebf5-124f-42f6-9463-33b00e711f03","model_name":"Gemini 3.5 Flash (high)","obs_id":"artificial_analysis:humanitys-last-exam:0097ebf5-124f-42f6-9463-33b00e711f03","organization":"Google","rank_in_source_response":23,"raw_value":"0.42678405931418","reported_by":"third_party","reported_date":"2026-05-19","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.42678405931418,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"794f69b5-cede-482b-b1cc-d769478497cd","model_name":"Grok 4.5 (high)","obs_id":"artificial_analysis:humanitys-last-exam:794f69b5-cede-482b-b1cc-d769478497cd","organization":"xAI","rank_in_source_response":23,"raw_value":"0.42678405931418","reported_by":"third_party","reported_date":"2026-07-08","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.42678405931418,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"59b5b14b-5365-4ee7-824a-18a8e6309644","model_name":"GPT-5.3 Codex (xhigh)","obs_id":"artificial_analysis:humanitys-last-exam:59b5b14b-5365-4ee7-824a-18a8e6309644","organization":"OpenAI","rank_in_source_response":25,"raw_value":"0.424930491195551","reported_by":"third_party","reported_date":"2026-02-05","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.424930491195551,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"8df710d3-9dae-4498-9b4e-9818238e6f31","model_name":"Qwen3.8 2.4T A95B","obs_id":"artificial_analysis:humanitys-last-exam:8df710d3-9dae-4498-9b4e-9818238e6f31","organization":"Qwen","rank_in_source_response":26,"raw_value":"0.424467099165894","reported_by":"third_party","reported_date":"2026-08-12","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.424467099165894,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"6b79f899-e3c0-45f6-923c-243faccdb2fc","model_name":"GPT-5.5 (medium)","obs_id":"artificial_analysis:humanitys-last-exam:6b79f899-e3c0-45f6-923c-243faccdb2fc","organization":"OpenAI","rank_in_source_response":27,"raw_value":"0.42354031510658","reported_by":"third_party","reported_date":"2026-04-23","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.42354031510658,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"e9a09db3-8fd6-41dd-ba2f-20e0a2bff7f2","model_name":"Claude Opus 4.7 (Adaptive Reasoning, Max Effort)","obs_id":"artificial_analysis:humanitys-last-exam:e9a09db3-8fd6-41dd-ba2f-20e0a2bff7f2","organization":"Anthropic","rank_in_source_response":28,"raw_value":"0.423076923076923","reported_by":"third_party","reported_date":"2026-04-16","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.423076923076923,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"cd684ea4-b475-4269-b001-d469d06d8a7a","model_name":"GLM-5.3 (max)","obs_id":"artificial_analysis:humanitys-last-exam:cd684ea4-b475-4269-b001-d469d06d8a7a","organization":"Z.ai","rank_in_source_response":29,"raw_value":"0.422613531047266","reported_by":"third_party","reported_date":"2026-08-18","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.422613531047266,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"6f174934-5b7d-4333-86cb-f5ebf4a862e3","model_name":"GPT-5.6 Sol (medium)","obs_id":"artificial_analysis:humanitys-last-exam:6f174934-5b7d-4333-86cb-f5ebf4a862e3","organization":"OpenAI","rank_in_source_response":30,"raw_value":"0.422150139017609","reported_by":"third_party","reported_date":"2026-07-09","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.422150139017609,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"26614164-6840-4e17-a65a-2deb2fe7e87b","model_name":"Grok 4.6 (medium)","obs_id":"artificial_analysis:humanitys-last-exam:26614164-6840-4e17-a65a-2deb2fe7e87b","organization":"xAI","rank_in_source_response":31,"raw_value":"0.421223354958295","reported_by":"third_party","reported_date":"2026-08-12","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.421223354958295,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"9e30696f-16fa-4b4f-ba53-161895a85fed","model_name":"GPT-5.6 Terra (xhigh)","obs_id":"artificial_analysis:humanitys-last-exam:9e30696f-16fa-4b4f-ba53-161895a85fed","organization":"OpenAI","rank_in_source_response":32,"raw_value":"0.418906394810009","reported_by":"third_party","reported_date":"2026-07-09","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.418906394810009,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"5016ea75-7b0e-4737-a7e6-1062c6d90fd4","model_name":"Gemini 3.5 Flash (medium)","obs_id":"artificial_analysis:humanitys-last-exam:5016ea75-7b0e-4737-a7e6-1062c6d90fd4","organization":"Google","rank_in_source_response":33,"raw_value":"0.413345690454124","reported_by":"third_party","reported_date":"2026-05-19","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.413345690454124,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"23c86e4a-c769-43c0-a056-79e3cd15834f","model_name":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort)","obs_id":"artificial_analysis:humanitys-last-exam:23c86e4a-c769-43c0-a056-79e3cd15834f","organization":"Anthropic","rank_in_source_response":34,"raw_value":"0.412882298424467","reported_by":"third_party","reported_date":"2026-06-30","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.412882298424467,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"f7a4ea75-e548-4069-80d4-9be8bc7c009b","model_name":"GLM-5.2 (max)","obs_id":"artificial_analysis:humanitys-last-exam:f7a4ea75-e548-4069-80d4-9be8bc7c009b","organization":"Z.ai","rank_in_source_response":35,"raw_value":"0.411492122335496","reported_by":"third_party","reported_date":"2026-06-16","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.411492122335496,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"83173329-c09a-41f1-a028-a282a5f908d7","model_name":"DeepSeek V4 Pro 0813 (Reasoning, Max Effort)","obs_id":"artificial_analysis:humanitys-last-exam:83173329-c09a-41f1-a028-a282a5f908d7","organization":"DeepSeek","rank_in_source_response":36,"raw_value":"0.410101946246525","reported_by":"third_party","reported_date":"2026-08-13","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.410101946246525,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"78332c88-fe60-42c8-af9d-3617e44cf1f5","model_name":"Gemini 3.6 Flash (high)","obs_id":"artificial_analysis:humanitys-last-exam:78332c88-fe60-42c8-af9d-3617e44cf1f5","organization":"Google","rank_in_source_response":37,"raw_value":"0.408248378127896","reported_by":"third_party","reported_date":"2026-07-21","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.408248378127896,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"ebf3b39f-0be6-43a1-a37a-f9b2978c9916","model_name":"Muse Spark","obs_id":"artificial_analysis:humanitys-last-exam:ebf3b39f-0be6-43a1-a37a-f9b2978c9916","organization":"Meta","rank_in_source_response":38,"raw_value":"0.406858202038925","reported_by":"third_party","reported_date":"2026-04-08","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.406858202038925,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"69534bed-2ffd-4235-832b-e20a810333ab","model_name":"Qwen3.7 Max","obs_id":"artificial_analysis:humanitys-last-exam:69534bed-2ffd-4235-832b-e20a810333ab","organization":"Qwen","rank_in_source_response":39,"raw_value":"0.405004633920297","reported_by":"third_party","reported_date":"2026-05-19","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.405004633920297,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"a3043d4f-9b92-4261-8ea2-a2d391b09cf4","model_name":"Motif 3 (Beta)","obs_id":"artificial_analysis:humanitys-last-exam:a3043d4f-9b92-4261-8ea2-a2d391b09cf4","organization":"Motif Technologies","rank_in_source_response":40,"raw_value":"0.403614457831325","reported_by":"third_party","reported_date":"2026-07-14","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.403614457831325,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"53c98840-47af-49aa-94e6-469fb17e9a1b","model_name":"Claude Opus 4.6 (Adaptive Reasoning, Max Effort)","obs_id":"artificial_analysis:humanitys-last-exam:53c98840-47af-49aa-94e6-469fb17e9a1b","organization":"Anthropic","rank_in_source_response":41,"raw_value":"0.399443929564411","reported_by":"third_party","reported_date":"2026-02-05","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.399443929564411,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"d1122eff-ee85-4fdc-8a9f-23bee6590667","model_name":"Gemini 3 Pro Preview (high)","obs_id":"artificial_analysis:humanitys-last-exam:d1122eff-ee85-4fdc-8a9f-23bee6590667","organization":"Google","rank_in_source_response":42,"raw_value":"0.397126969416126","reported_by":"third_party","reported_date":"2025-11-18","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.397126969416126,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"426d24c8-49ae-482a-b4a8-20f1c53f21c1","model_name":"GPT-5.6 Luna (max)","obs_id":"artificial_analysis:humanitys-last-exam:426d24c8-49ae-482a-b4a8-20f1c53f21c1","organization":"OpenAI","rank_in_source_response":43,"raw_value":"0.394810009267841","reported_by":"third_party","reported_date":"2026-07-09","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.394810009267841,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"0904b596-8932-43bd-9b21-324f128e1723","model_name":"GPT-5.6 Sol (low)","obs_id":"artificial_analysis:humanitys-last-exam:0904b596-8932-43bd-9b21-324f128e1723","organization":"OpenAI","rank_in_source_response":44,"raw_value":"0.393883225208526","reported_by":"third_party","reported_date":"2026-07-09","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.393883225208526,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"277f939a-985b-4b37-859d-b3eabc7c0b26","model_name":"MiniMax-M3","obs_id":"artificial_analysis:humanitys-last-exam:277f939a-985b-4b37-859d-b3eabc7c0b26","organization":"MiniMax","rank_in_source_response":45,"raw_value":"0.389712696941613","reported_by":"third_party","reported_date":"2026-06-01","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.389712696941613,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"eb0d4272-7204-42b9-b875-8866fed58548","model_name":"Gemini 3.7 Flash (medium)","obs_id":"artificial_analysis:humanitys-last-exam:eb0d4272-7204-42b9-b875-8866fed58548","organization":"Google","rank_in_source_response":45,"raw_value":"0.389712696941613","reported_by":"third_party","reported_date":"2026-08-13","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.389712696941613,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"fe4c0848-e284-4e52-a79d-cdc28392f1a9","model_name":"DeepSeek V4 Flash 0731 (Reasoning, Max Effort)","obs_id":"artificial_analysis:humanitys-last-exam:fe4c0848-e284-4e52-a79d-cdc28392f1a9","organization":"DeepSeek","rank_in_source_response":47,"raw_value":"0.385542168674699","reported_by":"third_party","reported_date":"2026-07-31","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.385542168674699,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"81972fba-1219-477e-bbfb-18c656a63ff7","model_name":"GPT-5.6 Terra (high)","obs_id":"artificial_analysis:humanitys-last-exam:81972fba-1219-477e-bbfb-18c656a63ff7","organization":"OpenAI","rank_in_source_response":48,"raw_value":"0.385078776645042","reported_by":"third_party","reported_date":"2026-07-09","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.385078776645042,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"0b7efa66-2115-49e0-a1b7-a2ba225fe9f6","model_name":"Grok Build 0.1 0616","obs_id":"artificial_analysis:humanitys-last-exam:0b7efa66-2115-49e0-a1b7-a2ba225fe9f6","organization":"xAI","rank_in_source_response":49,"raw_value":"0.382761816496756","reported_by":"third_party","reported_date":"2026-06-16","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.382761816496756,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"498862c3-f9ac-49d2-852f-16a02bb0c38f","model_name":"GPT-5.2 (xhigh)","obs_id":"artificial_analysis:humanitys-last-exam:498862c3-f9ac-49d2-852f-16a02bb0c38f","organization":"OpenAI","rank_in_source_response":50,"raw_value":"0.376737720111214","reported_by":"third_party","reported_date":"2025-12-11","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.376737720111214,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"bf220674-68bd-43cc-a1b8-ce5ed4d2f18d","model_name":"DeepSeek V4 Pro (Reasoning, Max Effort)","obs_id":"artificial_analysis:humanitys-last-exam:bf220674-68bd-43cc-a1b8-ce5ed4d2f18d","organization":"DeepSeek","rank_in_source_response":51,"raw_value":"0.375347544022243","reported_by":"third_party","reported_date":"2026-04-24","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.375347544022243,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"0de67206-4d36-4d10-b8f6-cf37fa747a03","model_name":"Kimi K2.6","obs_id":"artificial_analysis:humanitys-last-exam:0de67206-4d36-4d10-b8f6-cf37fa747a03","organization":"Moonshot AI","rank_in_source_response":52,"raw_value":"0.374884151992586","reported_by":"third_party","reported_date":"2026-04-20","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.374884151992586,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"948892b5-db03-4118-a4a8-ccd51ed871ea","model_name":"Grok 4.3 (high)","obs_id":"artificial_analysis:humanitys-last-exam:948892b5-db03-4118-a4a8-ccd51ed871ea","organization":"xAI","rank_in_source_response":53,"raw_value":"0.372103799814643","reported_by":"third_party","reported_date":"2026-04-30","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.372103799814643,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"87110ff0-1f79-41b4-9976-eda250597317","model_name":"GPT-5.6 Luna (xhigh)","obs_id":"artificial_analysis:humanitys-last-exam:87110ff0-1f79-41b4-9976-eda250597317","organization":"OpenAI","rank_in_source_response":54,"raw_value":"0.369786839666358","reported_by":"third_party","reported_date":"2026-07-09","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.369786839666358,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"b01eefb1-c9f8-412d-8353-571031a52f23","model_name":"Motif 3","obs_id":"artificial_analysis:humanitys-last-exam:b01eefb1-c9f8-412d-8353-571031a52f23","organization":"Motif Technologies","rank_in_source_response":54,"raw_value":"0.369786839666358","reported_by":"third_party","reported_date":"2026-08-12","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.369786839666358,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"7c73c3be-7f51-4d14-bec8-d5789488df25","model_name":"Gemini 3 Flash Preview (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:7c73c3be-7f51-4d14-bec8-d5789488df25","organization":"Google","rank_in_source_response":56,"raw_value":"0.365616311399444","reported_by":"third_party","reported_date":"2025-12-17","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.365616311399444,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"019e86f6-e66b-42d8-8a50-235a06b53003","model_name":"GPT-5.2 Codex (xhigh)","obs_id":"artificial_analysis:humanitys-last-exam:019e86f6-e66b-42d8-8a50-235a06b53003","organization":"OpenAI","rank_in_source_response":57,"raw_value":"0.357275254865616","reported_by":"third_party","reported_date":"2025-12-11","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.357275254865616,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"00f1248e-78e3-4230-8dc8-5e13ba8645e2","model_name":"MiMo-V2.5-Pro","obs_id":"artificial_analysis:humanitys-last-exam:00f1248e-78e3-4230-8dc8-5e13ba8645e2","organization":"Xiaomi","rank_in_source_response":58,"raw_value":"0.356811862835959","reported_by":"third_party","reported_date":"2026-04-22","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.356811862835959,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"a87fce42-eea3-4e45-a96d-fe057814f371","model_name":"Qwen3.7 Plus","obs_id":"artificial_analysis:humanitys-last-exam:a87fce42-eea3-4e45-a96d-fe057814f371","organization":"Qwen","rank_in_source_response":59,"raw_value":"0.356348470806302","reported_by":"third_party","reported_date":"2026-06-01","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.356348470806302,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"5da3c0e2-65d2-4bff-a410-cb2132ddafb6","model_name":"DeepSeek V4 Pro (Reasoning, High Effort)","obs_id":"artificial_analysis:humanitys-last-exam:5da3c0e2-65d2-4bff-a410-cb2132ddafb6","organization":"DeepSeek","rank_in_source_response":60,"raw_value":"0.352177942539388","reported_by":"third_party","reported_date":"2026-04-24","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.352177942539388,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"ddfdaf64-3f8e-40a6-a492-608ee83a1351","model_name":"Gemini 3.7 Flash (low)","obs_id":"artificial_analysis:humanitys-last-exam:ddfdaf64-3f8e-40a6-a492-608ee83a1351","organization":"Google","rank_in_source_response":61,"raw_value":"0.351251158480074","reported_by":"third_party","reported_date":"2026-08-13","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.351251158480074,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"8d0cb231-7303-452c-9923-a9620b948475","model_name":"Kimi K2.7 Code","obs_id":"artificial_analysis:humanitys-last-exam:8d0cb231-7303-452c-9923-a9620b948475","organization":"Moonshot AI","rank_in_source_response":62,"raw_value":"0.35032437442076","reported_by":"third_party","reported_date":"2026-06-12","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.35032437442076,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"d8ddb241-b3e4-4c25-a6a3-72eb1b30c541","model_name":"DeepSeek V4 Flash (Reasoning, Max Effort)","obs_id":"artificial_analysis:humanitys-last-exam:d8ddb241-b3e4-4c25-a6a3-72eb1b30c541","organization":"DeepSeek","rank_in_source_response":63,"raw_value":"0.348470806302132","reported_by":"third_party","reported_date":"2026-04-24","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.348470806302132,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"c72cb85a-18a4-4235-b455-77dff2f16c50","model_name":"Grok 4.20 0309 v2 (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:c72cb85a-18a4-4235-b455-77dff2f16c50","organization":"xAI","rank_in_source_response":64,"raw_value":"0.345227062094532","reported_by":"third_party","reported_date":"2026-04-07","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.345227062094532,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"7707a46f-895f-4247-b7a8-ddab87c9a11d","model_name":"DeepSeek V4 Flash Vision (Reasoning, Max Effort)","obs_id":"artificial_analysis:humanitys-last-exam:7707a46f-895f-4247-b7a8-ddab87c9a11d","organization":"DeepSeek","rank_in_source_response":65,"raw_value":"0.344763670064875","reported_by":"third_party","reported_date":"2026-08-21","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.344763670064875,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"b01dee41-c62b-48ed-8d16-984adc405e5c","model_name":"Qwen3.8 27B (xhigh)","obs_id":"artificial_analysis:humanitys-last-exam:b01dee41-c62b-48ed-8d16-984adc405e5c","organization":"Qwen","rank_in_source_response":66,"raw_value":"0.33920296570899","reported_by":"third_party","reported_date":"2026-08-14","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.33920296570899,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"3b5ba264-ad25-429b-a460-4d8698205f0d","model_name":"Nex-N2-Pro","obs_id":"artificial_analysis:humanitys-last-exam:3b5ba264-ad25-429b-a460-4d8698205f0d","organization":"Nex AGI","rank_in_source_response":67,"raw_value":"0.337349397590361","reported_by":"third_party","reported_date":"2026-06-02","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.337349397590361,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"5c3bdc0d-abab-4526-8079-34de4089bb4a","model_name":"LongCat 2.0","obs_id":"artificial_analysis:humanitys-last-exam:5c3bdc0d-abab-4526-8079-34de4089bb4a","organization":"LongCat","rank_in_source_response":68,"raw_value":"0.336886005560704","reported_by":"third_party","reported_date":"2026-06-29","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.336886005560704,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"fb112343-c82c-4b43-afea-996bd5101d62","model_name":"KAT-Coder-Pro V1","obs_id":"artificial_analysis:humanitys-last-exam:fb112343-c82c-4b43-afea-996bd5101d62","organization":"KwaiKAT","rank_in_source_response":69,"raw_value":"0.336422613531047","reported_by":"third_party","reported_date":"2025-11-11","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.336422613531047,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"8decf027-5114-4721-9ee1-81c0552980a0","model_name":"Agnes 2.5 Pro Alpha","obs_id":"artificial_analysis:humanitys-last-exam:8decf027-5114-4721-9ee1-81c0552980a0","organization":"Sapiens AI","rank_in_source_response":70,"raw_value":"0.33595922150139","reported_by":"third_party","reported_date":"2026-07-24","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.33595922150139,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"df8d14e0-3997-4e4d-b4ad-9c047acc9c69","model_name":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)","obs_id":"artificial_analysis:humanitys-last-exam:df8d14e0-3997-4e4d-b4ad-9c047acc9c69","organization":"Anthropic","rank_in_source_response":70,"raw_value":"0.33595922150139","reported_by":"third_party","reported_date":"2026-02-17","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.33595922150139,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"b23e6c69-96e5-44c9-8f58-4b42e0c399d5","model_name":"Hy3","obs_id":"artificial_analysis:humanitys-last-exam:b23e6c69-96e5-44c9-8f58-4b42e0c399d5","organization":"Tencent","rank_in_source_response":72,"raw_value":"0.334569045412419","reported_by":"third_party","reported_date":"2026-07-06","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.334569045412419,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"aa55297e-8fbf-4372-b4ab-9b068dc6396c","model_name":"GPT-5.6 Luna (high)","obs_id":"artificial_analysis:humanitys-last-exam:aa55297e-8fbf-4372-b4ab-9b068dc6396c","organization":"OpenAI","rank_in_source_response":73,"raw_value":"0.334105653382762","reported_by":"third_party","reported_date":"2026-07-09","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.334105653382762,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"2fa8e143-77a8-4d05-bfa8-d3b54634c00f","model_name":"Claude Opus 4.7 (Non-reasoning, High Effort)","obs_id":"artificial_analysis:humanitys-last-exam:2fa8e143-77a8-4d05-bfa8-d3b54634c00f","organization":"Anthropic","rank_in_source_response":74,"raw_value":"0.333178869323448","reported_by":"third_party","reported_date":"2026-04-16","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.333178869323448,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"7261504e-503c-4a66-a9d3-a3272cdf9ad6","model_name":"Inkling Small","obs_id":"artificial_analysis:humanitys-last-exam:7261504e-503c-4a66-a9d3-a3272cdf9ad6","organization":"Thinking Machines","rank_in_source_response":74,"raw_value":"0.333178869323448","reported_by":"third_party","reported_date":"2026-07-30","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.333178869323448,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"26e0f83a-ca98-4f34-94ac-7c5e251ee410","model_name":"GPT-5.6 Terra (medium)","obs_id":"artificial_analysis:humanitys-last-exam:26e0f83a-ca98-4f34-94ac-7c5e251ee410","organization":"OpenAI","rank_in_source_response":76,"raw_value":"0.332715477293791","reported_by":"third_party","reported_date":"2026-07-09","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.332715477293791,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"c77cfe51-f4a0-4692-9dee-5061ef667f23","model_name":"GPT-5.5 (low)","obs_id":"artificial_analysis:humanitys-last-exam:c77cfe51-f4a0-4692-9dee-5061ef667f23","organization":"OpenAI","rank_in_source_response":77,"raw_value":"0.326691380908248","reported_by":"third_party","reported_date":"2026-04-23","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.326691380908248,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"04787c2b-0751-4269-8029-075b727d7aed","model_name":"Grok 4.20 0309 (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:04787c2b-0751-4269-8029-075b727d7aed","organization":"xAI","rank_in_source_response":78,"raw_value":"0.323911028730306","reported_by":"third_party","reported_date":"2026-03-10","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.323911028730306,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"0de09623-2b1a-4c8d-86ef-7f5245d4e24b","model_name":"Inkling (xhigh)","obs_id":"artificial_analysis:humanitys-last-exam:0de09623-2b1a-4c8d-86ef-7f5245d4e24b","organization":"Thinking Machines","rank_in_source_response":79,"raw_value":"0.318813716404078","reported_by":"third_party","reported_date":"2026-07-15","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.318813716404078,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"538e945c-6c27-4fd3-995d-ded80a36cd10","model_name":"GPT-5.4 (low)","obs_id":"artificial_analysis:humanitys-last-exam:538e945c-6c27-4fd3-995d-ded80a36cd10","organization":"OpenAI","rank_in_source_response":80,"raw_value":"0.308155699721965","reported_by":"third_party","reported_date":"2026-03-05","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.308155699721965,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"6000692c-f9a6-47f8-a5c0-e0874ac488bb","model_name":"Qwen3.6 Max Preview","obs_id":"artificial_analysis:humanitys-last-exam:6000692c-f9a6-47f8-a5c0-e0874ac488bb","organization":"Qwen","rank_in_source_response":80,"raw_value":"0.308155699721965","reported_by":"third_party","reported_date":"2026-04-20","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.308155699721965,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"a550ffca-f89e-4381-ade6-a85dc6a1fb4c","model_name":"Kimi K2.5 (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:a550ffca-f89e-4381-ade6-a85dc6a1fb4c","organization":"Moonshot AI","rank_in_source_response":82,"raw_value":"0.307228915662651","reported_by":"third_party","reported_date":"2026-01-27","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.307228915662651,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"5d8183dc-24f4-46c5-a1d0-d937de149364","model_name":"MiMo-V2-Pro","obs_id":"artificial_analysis:humanitys-last-exam:5d8183dc-24f4-46c5-a1d0-d937de149364","organization":"Xiaomi","rank_in_source_response":83,"raw_value":"0.304448563484708","reported_by":"third_party","reported_date":"2026-03-18","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.304448563484708,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"89a2c945-1fab-4ee4-9f45-83a9f46cb221","model_name":"DeepSeek V4 Flash (Reasoning, High Effort)","obs_id":"artificial_analysis:humanitys-last-exam:89a2c945-1fab-4ee4-9f45-83a9f46cb221","organization":"DeepSeek","rank_in_source_response":84,"raw_value":"0.30259499536608","reported_by":"third_party","reported_date":"2026-04-24","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.30259499536608,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"2660d74f-ce79-48a8-8b53-6e668e2071a2","model_name":"Claude Opus 4.5 (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:2660d74f-ce79-48a8-8b53-6e668e2071a2","organization":"Anthropic","rank_in_source_response":85,"raw_value":"0.301204819277108","reported_by":"third_party","reported_date":"2025-11-24","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.301204819277108,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"5aa1c578-af76-4b91-8699-cdd43582b3af","model_name":"GLM-5.1 (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:5aa1c578-af76-4b91-8699-cdd43582b3af","organization":"Z.ai","rank_in_source_response":86,"raw_value":"0.300741427247451","reported_by":"third_party","reported_date":"2026-04-07","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.300741427247451,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"5e8b0d98-a3b4-42b5-93d8-ecb748788754","model_name":"Grok 4.3 (medium)","obs_id":"artificial_analysis:humanitys-last-exam:5e8b0d98-a3b4-42b5-93d8-ecb748788754","organization":"xAI","rank_in_source_response":87,"raw_value":"0.299814643188137","reported_by":"third_party","reported_date":"2026-04-30","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.299814643188137,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"4bbceacb-cf47-464b-b60f-e1d1fe016d67","model_name":"MiniMax-M2.7","obs_id":"artificial_analysis:humanitys-last-exam:4bbceacb-cf47-464b-b60f-e1d1fe016d67","organization":"MiniMax","rank_in_source_response":88,"raw_value":"0.29610750695088","reported_by":"third_party","reported_date":"2026-03-18","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.29610750695088,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"8215372b-66ff-457b-855e-e8abeafc9571","model_name":"A.X-K2","obs_id":"artificial_analysis:humanitys-last-exam:8215372b-66ff-457b-855e-e8abeafc9571","organization":"SK Telecom","rank_in_source_response":89,"raw_value":"0.295644114921223","reported_by":"third_party","reported_date":"2026-08-12","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.295644114921223,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"b2f3191f-77d6-4155-8be6-330f0baa1ae5","model_name":"Gemini 3 Pro Preview (low)","obs_id":"artificial_analysis:humanitys-last-exam:b2f3191f-77d6-4155-8be6-330f0baa1ae5","organization":"Google","rank_in_source_response":90,"raw_value":"0.294717330861909","reported_by":"third_party","reported_date":"2025-11-18","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.294717330861909,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"40663ad2-b218-471e-bdd4-a1e0c2360e2b","model_name":"GLM-5 (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:40663ad2-b218-471e-bdd4-a1e0c2360e2b","organization":"Z.ai","rank_in_source_response":91,"raw_value":"0.292863762743281","reported_by":"third_party","reported_date":"2026-02-11","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.292863762743281,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"1b64aa81-c223-4b8f-909b-82185a234765","model_name":"Solar Pro 4","obs_id":"artificial_analysis:humanitys-last-exam:1b64aa81-c223-4b8f-909b-82185a234765","organization":"Upstage","rank_in_source_response":92,"raw_value":"0.292400370713624","reported_by":"third_party","reported_date":"2026-08-06","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.292400370713624,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"cc4a20cd-09fe-4962-a430-119c815e85fa","model_name":"GPT-5.6 Terra (low)","obs_id":"artificial_analysis:humanitys-last-exam:cc4a20cd-09fe-4962-a430-119c815e85fa","organization":"OpenAI","rank_in_source_response":93,"raw_value":"0.291936978683967","reported_by":"third_party","reported_date":"2026-07-09","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.291936978683967,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"0e66bae9-41f1-42fc-9276-ce8cb6f72919","model_name":"Qwen3.5 397B A17B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:0e66bae9-41f1-42fc-9276-ce8cb6f72919","organization":"Qwen","rank_in_source_response":94,"raw_value":"0.289620018535681","reported_by":"third_party","reported_date":"2026-02-16","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.289620018535681,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"527e943a-adc6-4e69-93af-d1608e1b5fed","model_name":"DeepSeek V3.2 Speciale","obs_id":"artificial_analysis:humanitys-last-exam:527e943a-adc6-4e69-93af-d1608e1b5fed","organization":"DeepSeek","rank_in_source_response":95,"raw_value":"0.287303058387396","reported_by":"third_party","reported_date":"2025-12-01","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.287303058387396,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"7eabd8ca-bf43-4d56-b3df-efd1c4eebfb0","model_name":"Solar Open2 250B","obs_id":"artificial_analysis:humanitys-last-exam:7eabd8ca-bf43-4d56-b3df-efd1c4eebfb0","organization":"Upstage","rank_in_source_response":96,"raw_value":"0.285449490268767","reported_by":"third_party","reported_date":"2026-08-12","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.285449490268767,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"48e50f00-1fd1-4acc-b337-61078aa341e6","model_name":"GPT-5 (high)","obs_id":"artificial_analysis:humanitys-last-exam:48e50f00-1fd1-4acc-b337-61078aa341e6","organization":"OpenAI","rank_in_source_response":97,"raw_value":"0.28498609823911","reported_by":"third_party","reported_date":"2025-08-07","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.28498609823911,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"4dc12a38-b18f-4c43-8e1b-678f8434b5b1","model_name":"GPT-5.1 (high)","obs_id":"artificial_analysis:humanitys-last-exam:4dc12a38-b18f-4c43-8e1b-678f8434b5b1","organization":"OpenAI","rank_in_source_response":97,"raw_value":"0.28498609823911","reported_by":"third_party","reported_date":"2025-11-13","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.28498609823911,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"5b52def2-ac9b-4465-ad80-91ea8079e253","model_name":"Nemotron 3 Ultra 550B A55B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:5b52def2-ac9b-4465-ad80-91ea8079e253","organization":"NVIDIA","rank_in_source_response":99,"raw_value":"0.284059314179796","reported_by":"third_party","reported_date":"2026-06-04","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.284059314179796,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"d4fc3f33-f2b0-4da1-88ee-f1f82bd4de31","model_name":"GPT-5.4 nano (xhigh)","obs_id":"artificial_analysis:humanitys-last-exam:d4fc3f33-f2b0-4da1-88ee-f1f82bd4de31","organization":"OpenAI","rank_in_source_response":100,"raw_value":"0.282669138090825","reported_by":"third_party","reported_date":"2026-03-17","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.282669138090825,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"ba242e40-83b7-4cd3-a0e0-b56237984914","model_name":"GPT-5.4 mini (xhigh)","obs_id":"artificial_analysis:humanitys-last-exam:ba242e40-83b7-4cd3-a0e0-b56237984914","organization":"OpenAI","rank_in_source_response":101,"raw_value":"0.281278962001854","reported_by":"third_party","reported_date":"2026-03-17","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.281278962001854,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"806032ff-6252-4c22-ba99-a126e411b7a4","model_name":"Qwen3 Max Thinking","obs_id":"artificial_analysis:humanitys-last-exam:806032ff-6252-4c22-ba99-a126e411b7a4","organization":"Qwen","rank_in_source_response":102,"raw_value":"0.279888785912882","reported_by":"third_party","reported_date":"2026-01-26","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.279888785912882,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"64312f37-3701-4243-a4c9-7c07a58cd6b9","model_name":"Grok 4.20 0309 v2 (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:64312f37-3701-4243-a4c9-7c07a58cd6b9","organization":"xAI","rank_in_source_response":103,"raw_value":"0.279425393883225","reported_by":"third_party","reported_date":"2026-04-07","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.279425393883225,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"92f245a7-43b4-4ffd-8bfb-866746bf824d","model_name":"GLM-5.1 (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:92f245a7-43b4-4ffd-8bfb-866746bf824d","organization":"Z.ai","rank_in_source_response":103,"raw_value":"0.279425393883225","reported_by":"third_party","reported_date":"2026-04-07","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.279425393883225,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"5d11e7a1-4f70-4e5a-9364-e193761d6757","model_name":"GPT-5 Codex (high)","obs_id":"artificial_analysis:humanitys-last-exam:5d11e7a1-4f70-4e5a-9364-e193761d6757","organization":"OpenAI","rank_in_source_response":105,"raw_value":"0.278498609823911","reported_by":"third_party","reported_date":"2025-09-23","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.278498609823911,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"f371ad68-6947-4767-a78f-1f6c81f96b93","model_name":"Qwen3.6 Plus","obs_id":"artificial_analysis:humanitys-last-exam:f371ad68-6947-4767-a78f-1f6c81f96b93","organization":"Qwen","rank_in_source_response":105,"raw_value":"0.278498609823911","reported_by":"third_party","reported_date":"2026-04-02","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.278498609823911,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"149096f3-57b7-4413-80c2-a2c010a2995a","model_name":"GLM-5-Turbo","obs_id":"artificial_analysis:humanitys-last-exam:149096f3-57b7-4413-80c2-a2c010a2995a","organization":"Z.ai","rank_in_source_response":107,"raw_value":"0.277571825764597","reported_by":"third_party","reported_date":"2026-03-15","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.277571825764597,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"8ca48626-ff5e-48b3-8401-38081376d706","model_name":"Hy3-preview (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:8ca48626-ff5e-48b3-8401-38081376d706","organization":"Tencent","rank_in_source_response":107,"raw_value":"0.277571825764597","reported_by":"third_party","reported_date":"2026-04-23","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.277571825764597,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"c07e65e6-32fc-451e-938d-7477a1c3ffcc","model_name":"Grok 4.6 (low)","obs_id":"artificial_analysis:humanitys-last-exam:c07e65e6-32fc-451e-938d-7477a1c3ffcc","organization":"xAI","rank_in_source_response":109,"raw_value":"0.276181649675626","reported_by":"third_party","reported_date":"2026-08-12","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.276181649675626,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"6fc35842-0165-44cf-8570-c484a92b3d8c","model_name":"GLM-4.7 (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:6fc35842-0165-44cf-8570-c484a92b3d8c","organization":"Z.ai","rank_in_source_response":110,"raw_value":"0.27386468952734","reported_by":"third_party","reported_date":"2025-12-22","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.27386468952734,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"22d09131-343b-4adf-8760-533e20a2155f","model_name":"MiMo-V2.5","obs_id":"artificial_analysis:humanitys-last-exam:22d09131-343b-4adf-8760-533e20a2155f","organization":"Xiaomi","rank_in_source_response":111,"raw_value":"0.272011121408712","reported_by":"third_party","reported_date":"2026-04-22","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.272011121408712,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"5ea94a4a-55ac-4ea1-8898-2b3971e94af6","model_name":"Grok 4","obs_id":"artificial_analysis:humanitys-last-exam:5ea94a4a-55ac-4ea1-8898-2b3971e94af6","organization":"xAI","rank_in_source_response":112,"raw_value":"0.266913809082484","reported_by":"third_party","reported_date":"2025-07-10","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.266913809082484,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"84e3f11e-d659-4941-8988-1dbfabbaf538","model_name":"GPT-5.2 (medium)","obs_id":"artificial_analysis:humanitys-last-exam:84e3f11e-d659-4941-8988-1dbfabbaf538","organization":"OpenAI","rank_in_source_response":112,"raw_value":"0.266913809082484","reported_by":"third_party","reported_date":"2025-12-11","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.266913809082484,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"58b812bf-8498-46db-b834-f43ccc614b61","model_name":"GPT-5.6 Luna (medium)","obs_id":"artificial_analysis:humanitys-last-exam:58b812bf-8498-46db-b834-f43ccc614b61","organization":"OpenAI","rank_in_source_response":114,"raw_value":"0.257645968489342","reported_by":"third_party","reported_date":"2026-07-09","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.257645968489342,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"04d023f3-025c-4d78-9571-53edda3eaf2a","model_name":"GPT-5.1 Codex (high)","obs_id":"artificial_analysis:humanitys-last-exam:04d023f3-025c-4d78-9571-53edda3eaf2a","organization":"OpenAI","rank_in_source_response":115,"raw_value":"0.257182576459685","reported_by":"third_party","reported_date":"2025-11-13","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.257182576459685,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"5e965af0-ca5c-4f47-9ba9-06000508b84a","model_name":"GPT-5 (medium)","obs_id":"artificial_analysis:humanitys-last-exam:5e965af0-ca5c-4f47-9ba9-06000508b84a","organization":"OpenAI","rank_in_source_response":116,"raw_value":"0.253938832252085","reported_by":"third_party","reported_date":"2025-08-07","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.253938832252085,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"2236df45-0699-40d1-b5cc-69ee345d2257","model_name":"Qwen3.5 122B A10B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:2236df45-0699-40d1-b5cc-69ee345d2257","organization":"Qwen","rank_in_source_response":117,"raw_value":"0.252085264133457","reported_by":"third_party","reported_date":"2026-02-24","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.252085264133457,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"512d17ef-13d2-4f65-bf9b-154b0dec7e8d","model_name":"Kimi K3 (low)","obs_id":"artificial_analysis:humanitys-last-exam:512d17ef-13d2-4f65-bf9b-154b0dec7e8d","organization":"Moonshot AI","rank_in_source_response":118,"raw_value":"0.249768303985171","reported_by":"third_party","reported_date":"2026-07-16","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.249768303985171,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"d621247c-d47e-458c-82cb-a166bc3b37e5","model_name":"DeepSeek V3.2 (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:d621247c-d47e-458c-82cb-a166bc3b37e5","organization":"DeepSeek","rank_in_source_response":119,"raw_value":"0.245597775718258","reported_by":"third_party","reported_date":"2025-12-01","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.245597775718258,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"523125f4-a1da-4990-9abd-dd08a069100e","model_name":"Grok 4.20 0309 (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:523125f4-a1da-4990-9abd-dd08a069100e","organization":"xAI","rank_in_source_response":120,"raw_value":"0.245134383688601","reported_by":"third_party","reported_date":"2026-03-10","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.245134383688601,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"1aa3694e-b656-4dbe-8f84-0c65d8897abb","model_name":"Step 3.5 Flash 2603","obs_id":"artificial_analysis:humanitys-last-exam:1aa3694e-b656-4dbe-8f84-0c65d8897abb","organization":"StepFun","rank_in_source_response":121,"raw_value":"0.244670991658943","reported_by":"third_party","reported_date":"2026-04-02","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.244670991658943,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"033ade17-d9ec-44e0-b792-b5f1fcd5ab4c","model_name":"Gemini 3.5 Flash (minimal)","obs_id":"artificial_analysis:humanitys-last-exam:033ade17-d9ec-44e0-b792-b5f1fcd5ab4c","organization":"Google","rank_in_source_response":122,"raw_value":"0.240963855421687","reported_by":"third_party","reported_date":"2026-05-19","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.240963855421687,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"169e47f5-3d4d-4ad4-8f8b-ab46f0c73f67","model_name":"Qwen3.5 27B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:169e47f5-3d4d-4ad4-8f8b-ab46f0c73f67","organization":"Qwen","rank_in_source_response":123,"raw_value":"0.239110287303058","reported_by":"third_party","reported_date":"2026-02-24","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.239110287303058,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"bddebfd3-0a8d-47f5-b722-bc4c2ca5a5dc","model_name":"Kimi K2 Thinking","obs_id":"artificial_analysis:humanitys-last-exam:bddebfd3-0a8d-47f5-b722-bc4c2ca5a5dc","organization":"Moonshot AI","rank_in_source_response":124,"raw_value":"0.238183503243744","reported_by":"third_party","reported_date":"2025-11-06","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.238183503243744,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"e33dc369-ae81-40e0-8c4e-28b002d02197","model_name":"Ling 3.0 Flash","obs_id":"artificial_analysis:humanitys-last-exam:e33dc369-ae81-40e0-8c4e-28b002d02197","organization":"InclusionAI","rank_in_source_response":125,"raw_value":"0.236793327154773","reported_by":"third_party","reported_date":"2026-08-04","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.236793327154773,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"cd26a386-4873-46ff-b853-d239050025a2","model_name":"Gemma 4 31B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:cd26a386-4873-46ff-b853-d239050025a2","organization":"Google","rank_in_source_response":126,"raw_value":"0.236329935125116","reported_by":"third_party","reported_date":"2026-04-02","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.236329935125116,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"272ff333-442f-4169-a804-ac9177bc99d7","model_name":"MiniMax-M2.1","obs_id":"artificial_analysis:humanitys-last-exam:272ff333-442f-4169-a804-ac9177bc99d7","organization":"MiniMax","rank_in_source_response":127,"raw_value":"0.231696014828545","reported_by":"third_party","reported_date":"2025-12-23","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.231696014828545,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"8c29d66d-bf98-4ea3-8572-5409353ecc66","model_name":"Qwen3.6 27B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:8c29d66d-bf98-4ea3-8572-5409353ecc66","organization":"Qwen","rank_in_source_response":128,"raw_value":"0.230769230769231","reported_by":"third_party","reported_date":"2026-04-22","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.230769230769231,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"be185709-ddb4-4268-9597-856464359b25","model_name":"MiMo-V2-Flash (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:be185709-ddb4-4268-9597-856464359b25","organization":"Xiaomi","rank_in_source_response":129,"raw_value":"0.228452270620945","reported_by":"third_party","reported_date":"2025-12-16","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.228452270620945,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"296ace9b-0815-43b2-bafa-fd6cec5cce36","model_name":"MiMo-V2-Omni-0327","obs_id":"artificial_analysis:humanitys-last-exam:296ace9b-0815-43b2-bafa-fd6cec5cce36","organization":"Xiaomi","rank_in_source_response":130,"raw_value":"0.225671918443003","reported_by":"third_party","reported_date":"2026-03-27","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.225671918443003,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"27202e5f-c82d-4710-92e9-4317877d4883","model_name":"Gemini 2.5 Pro","obs_id":"artificial_analysis:humanitys-last-exam:27202e5f-c82d-4710-92e9-4317877d4883","organization":"Google","rank_in_source_response":131,"raw_value":"0.225208526413346","reported_by":"third_party","reported_date":"2025-06-05","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.225208526413346,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"8665ca00-c687-44c7-875c-22618cb31c4f","model_name":"Qwen3.6 35B A3B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:8665ca00-c687-44c7-875c-22618cb31c4f","organization":"Qwen","rank_in_source_response":132,"raw_value":"0.222428174235403","reported_by":"third_party","reported_date":"2026-04-16","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.222428174235403,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"1479f50b-d37f-4b55-bb8b-4212a15042eb","model_name":"MiMo-V2-Flash (Feb 2026)","obs_id":"artificial_analysis:humanitys-last-exam:1479f50b-d37f-4b55-bb8b-4212a15042eb","organization":"Xiaomi","rank_in_source_response":133,"raw_value":"0.221037998146432","reported_by":"third_party","reported_date":"2025-12-16","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.221037998146432,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"94d09368-9035-47cf-963a-b4310b433a16","model_name":"MiMo-V2-Omni","obs_id":"artificial_analysis:humanitys-last-exam:94d09368-9035-47cf-963a-b4310b433a16","organization":"Xiaomi","rank_in_source_response":133,"raw_value":"0.221037998146432","reported_by":"third_party","reported_date":"2026-03-19","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.221037998146432,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"583f98fb-c4b8-4df3-8d40-60ac0ed69882","model_name":"Muse Glimmer (high)","obs_id":"artificial_analysis:humanitys-last-exam:583f98fb-c4b8-4df3-8d40-60ac0ed69882","organization":"Meta","rank_in_source_response":135,"raw_value":"0.219647822057461","reported_by":"third_party","reported_date":"2026-08-10","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.219647822057461,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"e34ffffb-d8e1-4f5c-a2c7-3ca19c235eeb","model_name":"GPT-5.5 Instant (May 2026)","obs_id":"artificial_analysis:humanitys-last-exam:e34ffffb-d8e1-4f5c-a2c7-3ca19c235eeb","organization":"OpenAI","rank_in_source_response":136,"raw_value":"0.215940685820204","reported_by":"third_party","reported_date":"2026-05-05","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.215940685820204,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"eb4ba465-3fcd-4065-9fe2-e8225e7b2c6c","model_name":"Ring-2.6-1T","obs_id":"artificial_analysis:humanitys-last-exam:eb4ba465-3fcd-4065-9fe2-e8225e7b2c6c","organization":"InclusionAI","rank_in_source_response":136,"raw_value":"0.215940685820204","reported_by":"third_party","reported_date":"2026-05-08","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.215940685820204,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"29855680-7469-43eb-8b88-cd3fb1d99da3","model_name":"GPT-5 mini (high)","obs_id":"artificial_analysis:humanitys-last-exam:29855680-7469-43eb-8b88-cd3fb1d99da3","organization":"OpenAI","rank_in_source_response":138,"raw_value":"0.214550509731233","reported_by":"third_party","reported_date":"2025-08-07","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.214550509731233,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"6c7b322e-2f35-48ff-9171-fb621a726fc0","model_name":"Step 3.7 Flash","obs_id":"artificial_analysis:humanitys-last-exam:6c7b322e-2f35-48ff-9171-fb621a726fc0","organization":"StepFun","rank_in_source_response":139,"raw_value":"0.214087117701576","reported_by":"third_party","reported_date":"2026-05-29","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.214087117701576,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"c8158c23-6fff-4c31-911d-954c32d80c28","model_name":"Step 3.5 Flash","obs_id":"artificial_analysis:humanitys-last-exam:c8158c23-6fff-4c31-911d-954c32d80c28","organization":"StepFun","rank_in_source_response":140,"raw_value":"0.211306765523633","reported_by":"third_party","reported_date":"2026-02-02","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.211306765523633,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"46d8315e-1630-463f-ab62-84185fa0faab","model_name":"Qwen3.5 35B A3B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:46d8315e-1630-463f-ab62-84185fa0faab","organization":"Qwen","rank_in_source_response":141,"raw_value":"0.210379981464319","reported_by":"third_party","reported_date":"2026-02-24","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.210379981464319,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"63872e9c-3377-4a6b-b477-7bba244c38e9","model_name":"Nemotron 3 Super 120B A12B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:63872e9c-3377-4a6b-b477-7bba244c38e9","organization":"NVIDIA","rank_in_source_response":142,"raw_value":"0.207599629286376","reported_by":"third_party","reported_date":"2026-03-11","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.207599629286376,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"12adec16-19fe-4d92-aeff-5ef3eb7e780a","model_name":"MiniMax-M2.5","obs_id":"artificial_analysis:humanitys-last-exam:12adec16-19fe-4d92-aeff-5ef3eb7e780a","organization":"MiniMax","rank_in_source_response":143,"raw_value":"0.205282669138091","reported_by":"third_party","reported_date":"2026-02-12","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.205282669138091,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"16c5b637-8bce-4252-81f2-1b87a36a4e4c","model_name":"o3","obs_id":"artificial_analysis:humanitys-last-exam:16c5b637-8bce-4252-81f2-1b87a36a4e4c","organization":"OpenAI","rank_in_source_response":144,"raw_value":"0.2005","reported_by":"third_party","reported_date":"2025-04-16","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.2005,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"073b5329-c4b3-4f1f-8f97-4753aadf4398","model_name":"Gemini 2.5 Pro Preview (May' 25)","obs_id":"artificial_analysis:humanitys-last-exam:073b5329-c4b3-4f1f-8f97-4753aadf4398","organization":"Google","rank_in_source_response":145,"raw_value":"0.1993","reported_by":"third_party","reported_date":"2025-05-06","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.1993,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"c4169d75-9d24-4794-a9c3-69e1fe364de5","model_name":"GPT-5.5 Instant (June 2026)","obs_id":"artificial_analysis:humanitys-last-exam:c4169d75-9d24-4794-a9c3-69e1fe364de5","organization":"OpenAI","rank_in_source_response":146,"raw_value":"0.199258572752549","reported_by":"third_party","reported_date":"2026-06-25","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.199258572752549,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"050c61cd-cddc-463a-a30a-a82aaa37be59","model_name":"GPT-5.6 Luna (low)","obs_id":"artificial_analysis:humanitys-last-exam:050c61cd-cddc-463a-a30a-a82aaa37be59","organization":"OpenAI","rank_in_source_response":147,"raw_value":"0.198331788693234","reported_by":"third_party","reported_date":"2026-07-09","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.198331788693234,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"30ef2a79-e800-4165-9f13-2a338f120db7","model_name":"Qwen3.5 397B A17B (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:30ef2a79-e800-4165-9f13-2a338f120db7","organization":"Qwen","rank_in_source_response":147,"raw_value":"0.198331788693234","reported_by":"third_party","reported_date":"2026-02-16","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.198331788693234,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"f0083258-8646-45b8-8082-7aaf6c2ea82a","model_name":"gpt-oss-120b (high)","obs_id":"artificial_analysis:humanitys-last-exam:f0083258-8646-45b8-8082-7aaf6c2ea82a","organization":"OpenAI","rank_in_source_response":149,"raw_value":"0.196014828544949","reported_by":"third_party","reported_date":"2025-08-05","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.196014828544949,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"0fc6308e-fbd2-42d3-a216-06da3c43e34e","model_name":"Kimi K2.6 (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:0fc6308e-fbd2-42d3-a216-06da3c43e34e","organization":"Moonshot AI","rank_in_source_response":150,"raw_value":"0.195551436515292","reported_by":"third_party","reported_date":"2026-04-20","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.195551436515292,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"7f3c9423-3ee3-4369-a6d9-3f2a40aff00e","model_name":"GPT-5 (low)","obs_id":"artificial_analysis:humanitys-last-exam:7f3c9423-3ee3-4369-a6d9-3f2a40aff00e","organization":"OpenAI","rank_in_source_response":150,"raw_value":"0.195551436515292","reported_by":"third_party","reported_date":"2025-08-07","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.195551436515292,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"23149f9b-c904-43e2-9ec4-afa2bf843941","model_name":"Grok 4.1 Fast (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:23149f9b-c904-43e2-9ec4-afa2bf843941","organization":"xAI","rank_in_source_response":152,"raw_value":"0.193234476367006","reported_by":"third_party","reported_date":"2025-11-19","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.193234476367006,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"6e1b44ff-c227-496b-aef4-19b70cd18c76","model_name":"Gemma 4 26B A4B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:6e1b44ff-c227-496b-aef4-19b70cd18c76","organization":"Google","rank_in_source_response":152,"raw_value":"0.193234476367006","reported_by":"third_party","reported_date":"2026-04-02","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.193234476367006,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"4386585e-71b4-4a0c-8a63-afb333419cd6","model_name":"Claude Opus 4.6 (Non-reasoning, High Effort)","obs_id":"artificial_analysis:humanitys-last-exam:4386585e-71b4-4a0c-8a63-afb333419cd6","organization":"Anthropic","rank_in_source_response":154,"raw_value":"0.190917516218721","reported_by":"third_party","reported_date":"2026-02-05","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.190917516218721,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"573bbd93-114c-4b71-9ede-a73a7d4bdf84","model_name":"Grok 4 Fast (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:573bbd93-114c-4b71-9ede-a73a7d4bdf84","organization":"xAI","rank_in_source_response":154,"raw_value":"0.190917516218721","reported_by":"third_party","reported_date":"2025-09-19","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.190917516218721,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"d58b9ada-fd9d-4fff-a086-242034657963","model_name":"Claude Sonnet 5 (Non-reasoning, High Effort)","obs_id":"artificial_analysis:humanitys-last-exam:d58b9ada-fd9d-4fff-a086-242034657963","organization":"Anthropic","rank_in_source_response":156,"raw_value":"0.190454124189064","reported_by":"third_party","reported_date":"2026-06-30","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.190454124189064,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"093b9df2-ebee-4309-943f-5a7e88360adf","model_name":"Gemini 3.5 Flash-Lite","obs_id":"artificial_analysis:humanitys-last-exam:093b9df2-ebee-4309-943f-5a7e88360adf","organization":"Google","rank_in_source_response":157,"raw_value":"0.188137164040778","reported_by":"third_party","reported_date":"2026-07-21","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.188137164040778,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"18721247-4e56-4cf7-9a9d-c71cc60c0961","model_name":"K-EXAONE 2.0 0803","obs_id":"artificial_analysis:humanitys-last-exam:18721247-4e56-4cf7-9a9d-c71cc60c0961","organization":"LG AI Research","rank_in_source_response":158,"raw_value":"0.185820203892493","reported_by":"third_party","reported_date":"2026-08-12","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.185820203892493,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"392063ba-c3b5-47e8-ba67-a7b0b34f6824","model_name":"GPT-5.4 mini (medium)","obs_id":"artificial_analysis:humanitys-last-exam:392063ba-c3b5-47e8-ba67-a7b0b34f6824","organization":"OpenAI","rank_in_source_response":158,"raw_value":"0.185820203892493","reported_by":"third_party","reported_date":"2026-03-17","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.185820203892493,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"fd4454ff-e703-46c0-a7f5-fa69af09486d","model_name":"GPT-5.1 Codex mini (high)","obs_id":"artificial_analysis:humanitys-last-exam:fd4454ff-e703-46c0-a7f5-fa69af09486d","organization":"OpenAI","rank_in_source_response":160,"raw_value":"0.184893419833179","reported_by":"third_party","reported_date":"2025-11-13","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.184893419833179,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"fe2c2289-d261-4433-8681-46448372c1f6","model_name":"Grok 4.3 (low)","obs_id":"artificial_analysis:humanitys-last-exam:fe2c2289-d261-4433-8681-46448372c1f6","organization":"xAI","rank_in_source_response":161,"raw_value":"0.183503243744208","reported_by":"third_party","reported_date":"2026-04-30","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.183503243744208,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"62de31e8-a1a3-429c-b634-a2afccfd9363","model_name":"Gemini 2.5 Pro Preview (Mar' 25)","obs_id":"artificial_analysis:humanitys-last-exam:62de31e8-a1a3-429c-b634-a2afccfd9363","organization":"Google","rank_in_source_response":162,"raw_value":"0.180259499536608","reported_by":"third_party","reported_date":"2025-03-25","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.180259499536608,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"901ec71b-51ec-4f53-b807-06ee17b890b4","model_name":"JT-4.1 Flash 236B A21B","obs_id":"artificial_analysis:humanitys-last-exam:901ec71b-51ec-4f53-b807-06ee17b890b4","organization":"China Mobile","rank_in_source_response":163,"raw_value":"0.177942539388323","reported_by":"third_party","reported_date":"2026-07-09","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.177942539388323,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"90e078f2-051b-4c63-8919-76618971cb3f","model_name":"Claude 4.5 Sonnet (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:90e078f2-051b-4c63-8919-76618971cb3f","organization":"Anthropic","rank_in_source_response":163,"raw_value":"0.177942539388323","reported_by":"third_party","reported_date":"2025-09-29","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.177942539388323,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"c1c5db7c-968f-445a-a274-7b5689348bf8","model_name":"G9v3-39A5B","obs_id":"artificial_analysis:humanitys-last-exam:c1c5db7c-968f-445a-a274-7b5689348bf8","organization":"AI9Stars","rank_in_source_response":165,"raw_value":"0.174698795180723","reported_by":"third_party","reported_date":"2026-08-20","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.174698795180723,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"598190f8-dc9c-4fea-a7ea-4b81c402ab18","model_name":"Gemini 3.1 Flash-Lite","obs_id":"artificial_analysis:humanitys-last-exam:598190f8-dc9c-4fea-a7ea-4b81c402ab18","organization":"Google","rank_in_source_response":166,"raw_value":"0.17191844300278","reported_by":"third_party","reported_date":"2026-03-03","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.17191844300278,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"016d330a-2141-4afa-b2fc-62b314423dc1","model_name":"Mercury 2","obs_id":"artificial_analysis:humanitys-last-exam:016d330a-2141-4afa-b2fc-62b314423dc1","organization":"Inception","rank_in_source_response":167,"raw_value":"0.171455050973123","reported_by":"third_party","reported_date":"2026-02-20","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.171455050973123,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"248deb0d-426c-4fa9-86fa-bc60aa9c3719","model_name":"GLM 5V Turbo (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:248deb0d-426c-4fa9-86fa-bc60aa9c3719","organization":"Z.ai","rank_in_source_response":167,"raw_value":"0.171455050973123","reported_by":"third_party","reported_date":"2026-04-01","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.171455050973123,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"7c4d1e30-6ecb-46cf-880c-41446d7b51f1","model_name":"GPT-5.6 Sol (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:7c4d1e30-6ecb-46cf-880c-41446d7b51f1","organization":"OpenAI","rank_in_source_response":169,"raw_value":"0.166821130676552","reported_by":"third_party","reported_date":"2026-07-09","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.166821130676552,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"340fb211-4fad-41d3-87d5-ed0d0cd34088","model_name":"HyperNova 60B 2605","obs_id":"artificial_analysis:humanitys-last-exam:340fb211-4fad-41d3-87d5-ed0d0cd34088","organization":"Multiverse Computing","rank_in_source_response":170,"raw_value":"0.166357738646895","reported_by":"third_party","reported_date":"2026-05-26","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.166357738646895,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"84b49308-6b93-47aa-a4f6-776ee1a1e8cd","model_name":"o4-mini (high)","obs_id":"artificial_analysis:humanitys-last-exam:84b49308-6b93-47aa-a4f6-776ee1a1e8cd","organization":"OpenAI","rank_in_source_response":171,"raw_value":"0.165430954587581","reported_by":"third_party","reported_date":"2025-04-16","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.165430954587581,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"0a7dda4d-cc9c-4a90-abc1-abb5772c901b","model_name":"DeepSeek V3.1 Terminus (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:0a7dda4d-cc9c-4a90-abc1-abb5772c901b","organization":"DeepSeek","rank_in_source_response":172,"raw_value":"0.163577386468953","reported_by":"third_party","reported_date":"2025-09-22","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.163577386468953,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"fc4223e8-4586-4ca1-97ca-bb55ff586947","model_name":"KAT Coder Pro V2","obs_id":"artificial_analysis:humanitys-last-exam:fc4223e8-4586-4ca1-97ca-bb55ff586947","organization":"KwaiKAT","rank_in_source_response":173,"raw_value":"0.161260426320667","reported_by":"third_party","reported_date":"2026-03-27","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.161260426320667,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"021b1b31-d2fc-4653-ab74-c10bd2f41c8e","model_name":"Qwen3.5 122B A10B (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:021b1b31-d2fc-4653-ab74-c10bd2f41c8e","organization":"Qwen","rank_in_source_response":174,"raw_value":"0.159406858202039","reported_by":"third_party","reported_date":"2026-02-24","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.159406858202039,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"8869f28a-a6ff-487f-8d32-93fe335fdda5","model_name":"GPT-5.4 nano (medium)","obs_id":"artificial_analysis:humanitys-last-exam:8869f28a-a6ff-487f-8d32-93fe335fdda5","organization":"OpenAI","rank_in_source_response":174,"raw_value":"0.159406858202039","reported_by":"third_party","reported_date":"2026-03-17","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.159406858202039,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"c3274a19-6d3c-4d01-ab9b-5055a0a40429","model_name":"GPT-5 mini (medium)","obs_id":"artificial_analysis:humanitys-last-exam:c3274a19-6d3c-4d01-ab9b-5055a0a40429","organization":"OpenAI","rank_in_source_response":174,"raw_value":"0.159406858202039","reported_by":"third_party","reported_date":"2025-08-07","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.159406858202039,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"f6ccbe1d-bd7e-484b-9795-18cc9f91552d","model_name":"Qwen3 235B A22B 2507 (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:f6ccbe1d-bd7e-484b-9795-18cc9f91552d","organization":"Qwen","rank_in_source_response":177,"raw_value":"0.158943466172382","reported_by":"third_party","reported_date":"2025-07-25","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.158943466172382,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"a83f84b3-473a-4276-9ae1-8909da723159","model_name":"DeepSeek R1 0528 (May '25)","obs_id":"artificial_analysis:humanitys-last-exam:a83f84b3-473a-4276-9ae1-8909da723159","organization":"DeepSeek","rank_in_source_response":178,"raw_value":"0.158480074142725","reported_by":"third_party","reported_date":"2025-05-28","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.158480074142725,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"b6d2e43d-3082-43f5-9318-0f4dbcb54163","model_name":"Trinity Large Thinking","obs_id":"artificial_analysis:humanitys-last-exam:b6d2e43d-3082-43f5-9318-0f4dbcb54163","organization":"Arcee AI","rank_in_source_response":178,"raw_value":"0.158480074142725","reported_by":"third_party","reported_date":"2026-04-01","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.158480074142725,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"feb02d3b-ff8d-4ed4-b165-13f8d4a7192c","model_name":"Gemma 4 12B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:feb02d3b-ff8d-4ed4-b165-13f8d4a7192c","organization":"Google","rank_in_source_response":180,"raw_value":"0.156626506024096","reported_by":"third_party","reported_date":"2026-06-03","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.156626506024096,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"3b156101-b0d7-4438-b350-2d1f1168f40a","model_name":"Qwen3.6 27B (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:3b156101-b0d7-4438-b350-2d1f1168f40a","organization":"Qwen","rank_in_source_response":181,"raw_value":"0.150602409638554","reported_by":"third_party","reported_date":"2026-04-22","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.150602409638554,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"783a0ea2-1eef-422a-8c3d-f6d40d943f54","model_name":"Gemini 3 Flash Preview (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:783a0ea2-1eef-422a-8c3d-f6d40d943f54","organization":"Google","rank_in_source_response":182,"raw_value":"0.14967562557924","reported_by":"third_party","reported_date":"2025-12-17","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.14967562557924,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"2d28a13a-096e-475a-beb8-26bbd1c7d51c","model_name":"Qwen3.5 9B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:2d28a13a-096e-475a-beb8-26bbd1c7d51c","organization":"Qwen","rank_in_source_response":183,"raw_value":"0.149212233549583","reported_by":"third_party","reported_date":"2026-03-02","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.149212233549583,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"0179b427-93dc-415c-bb4c-f980ddf8d088","model_name":"Qwen3.5 Omni Plus","obs_id":"artificial_analysis:humanitys-last-exam:0179b427-93dc-415c-bb4c-f980ddf8d088","organization":"Qwen","rank_in_source_response":184,"raw_value":"0.148748841519926","reported_by":"third_party","reported_date":"2026-03-30","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.148748841519926,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"af134350-8ba3-4629-b56b-00bd6dcf60c4","model_name":"DeepSeek V3.2 Exp (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:af134350-8ba3-4629-b56b-00bd6dcf60c4","organization":"DeepSeek","rank_in_source_response":184,"raw_value":"0.148748841519926","reported_by":"third_party","reported_date":"2025-09-29","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.148748841519926,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"4764d31d-f4af-4297-8bd1-e993f26bcb64","model_name":"MiMo-V2.5-Pro (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:4764d31d-f4af-4297-8bd1-e993f26bcb64","organization":"Xiaomi","rank_in_source_response":186,"raw_value":"0.147822057460612","reported_by":"third_party","reported_date":"2026-04-22","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.147822057460612,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"6a5d56e1-bb68-4205-8d9b-26b97888bc84","model_name":"GLM-4.6 (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:6a5d56e1-bb68-4205-8d9b-26b97888bc84","organization":"Z.ai","rank_in_source_response":187,"raw_value":"0.144578313253012","reported_by":"third_party","reported_date":"2025-09-30","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.144578313253012,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"198b717f-42c8-4ab7-a699-ae9373d669d3","model_name":"DeepSeek V3.1 (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:198b717f-42c8-4ab7-a699-ae9373d669d3","organization":"DeepSeek","rank_in_source_response":188,"raw_value":"0.142724745134384","reported_by":"third_party","reported_date":"2025-08-21","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.142724745134384,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"4d6dd5ce-08cb-4e87-9288-1dd2f022aa35","model_name":"Doubao Seed Code","obs_id":"artificial_analysis:humanitys-last-exam:4d6dd5ce-08cb-4e87-9288-1dd2f022aa35","organization":"ByteDance Seed","rank_in_source_response":189,"raw_value":"0.140871177015755","reported_by":"third_party","reported_date":"2025-11-11","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.140871177015755,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"6657d7de-a2a9-40bc-a32f-86e80ad63698","model_name":"Qwen3.8 27B (medium)","obs_id":"artificial_analysis:humanitys-last-exam:6657d7de-a2a9-40bc-a32f-86e80ad63698","organization":"Qwen","rank_in_source_response":189,"raw_value":"0.140871177015755","reported_by":"third_party","reported_date":"2026-08-14","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.140871177015755,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"7e30585f-fad7-40df-a8cb-03c1d96df38a","model_name":"Qwen3.8 27B (low)","obs_id":"artificial_analysis:humanitys-last-exam:7e30585f-fad7-40df-a8cb-03c1d96df38a","organization":"Qwen","rank_in_source_response":191,"raw_value":"0.140407784986098","reported_by":"third_party","reported_date":"2026-08-14","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.140407784986098,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"509e94e3-f1cb-43fb-98ff-e0e9872cfd1f","model_name":"Qwen3.5 27B (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:509e94e3-f1cb-43fb-98ff-e0e9872cfd1f","organization":"Qwen","rank_in_source_response":192,"raw_value":"0.139481000926784","reported_by":"third_party","reported_date":"2026-02-24","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.139481000926784,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"715e05fb-1313-441c-bf1d-8651c752a841","model_name":"K-EXAONE (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:715e05fb-1313-441c-bf1d-8651c752a841","organization":"LG AI Research","rank_in_source_response":192,"raw_value":"0.139481000926784","reported_by":"third_party","reported_date":"2025-12-31","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.139481000926784,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"66938aab-78fa-49d7-8461-b48b6833e837","model_name":"Qwen3.6 35B A3B (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:66938aab-78fa-49d7-8461-b48b6833e837","organization":"Qwen","rank_in_source_response":194,"raw_value":"0.139017608897127","reported_by":"third_party","reported_date":"2026-04-16","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.139017608897127,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"c7667559-d9b6-43f1-8cd8-8bdbc78d190b","model_name":"Gemini 2.5 Flash Preview (Sep '25) (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:c7667559-d9b6-43f1-8cd8-8bdbc78d190b","organization":"Google","rank_in_source_response":195,"raw_value":"0.138090824837813","reported_by":"third_party","reported_date":"2025-09-25","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.138090824837813,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"dd059b25-d82a-4ead-82a4-4adceaaec48b","model_name":"Mistral Medium 3.5","obs_id":"artificial_analysis:humanitys-last-exam:dd059b25-d82a-4ead-82a4-4adceaaec48b","organization":"Mistral","rank_in_source_response":196,"raw_value":"0.137627432808156","reported_by":"third_party","reported_date":"2026-04-29","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.137627432808156,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"6f1a7562-6e96-46ac-af4f-6ba5a7a3da96","model_name":"GPT-5.5 (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:6f1a7562-6e96-46ac-af4f-6ba5a7a3da96","organization":"OpenAI","rank_in_source_response":197,"raw_value":"0.137164040778499","reported_by":"third_party","reported_date":"2026-04-23","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.137164040778499,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"f74ea286-cd29-4eb4-af14-1389b19c21e5","model_name":"MiniMax-M2","obs_id":"artificial_analysis:humanitys-last-exam:f74ea286-cd29-4eb4-af14-1389b19c21e5","organization":"MiniMax","rank_in_source_response":198,"raw_value":"0.136700648748842","reported_by":"third_party","reported_date":"2025-10-26","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.136700648748842,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"eebfef01-709e-4ffe-b72f-0db75ef2434b","model_name":"Qwen3.5 35B A3B (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:eebfef01-709e-4ffe-b72f-0db75ef2434b","organization":"Qwen","rank_in_source_response":199,"raw_value":"0.134383688600556","reported_by":"third_party","reported_date":"2026-02-24","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.134383688600556,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"2e40e695-3cec-43da-83f9-615af30b8e91","model_name":"Claude Sonnet 4.6 (Non-reasoning, High Effort)","obs_id":"artificial_analysis:humanitys-last-exam:2e40e695-3cec-43da-83f9-615af30b8e91","organization":"Anthropic","rank_in_source_response":200,"raw_value":"0.133456904541242","reported_by":"third_party","reported_date":"2026-02-17","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.133456904541242,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"a518a64b-e337-48f3-85a1-ba7dc0e8f961","model_name":"ERNIE 5.0 Thinking Preview","obs_id":"artificial_analysis:humanitys-last-exam:a518a64b-e337-48f3-85a1-ba7dc0e8f961","organization":"Baidu","rank_in_source_response":201,"raw_value":"0.132530120481928","reported_by":"third_party","reported_date":"2025-11-13","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.132530120481928,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"4077490a-bbfb-404e-979a-a97a20e3b5de","model_name":"Claude Opus 4.5 (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:4077490a-bbfb-404e-979a-a97a20e3b5de","organization":"Anthropic","rank_in_source_response":202,"raw_value":"0.131603336422614","reported_by":"third_party","reported_date":"2025-11-24","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.131603336422614,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"ba04694d-326a-4a6a-8f1b-46316f872a7f","model_name":"Kimi K2.5 (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:ba04694d-326a-4a6a-8f1b-46316f872a7f","organization":"Moonshot AI","rank_in_source_response":202,"raw_value":"0.131603336422614","reported_by":"third_party","reported_date":"2026-01-27","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.131603336422614,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"369329e4-629f-425d-975a-e8980aec2965","model_name":"INTELLECT-3","obs_id":"artificial_analysis:humanitys-last-exam:369329e4-629f-425d-975a-e8980aec2965","organization":"Prime Intellect","rank_in_source_response":204,"raw_value":"0.130676552363299","reported_by":"third_party","reported_date":"2025-11-27","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.130676552363299,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"1cf439b8-0cfd-47b2-9de2-9a2157e6762b","model_name":"GLM-4.5 (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:1cf439b8-0cfd-47b2-9de2-9a2157e6762b","organization":"Z.ai","rank_in_source_response":205,"raw_value":"0.129749768303985","reported_by":"third_party","reported_date":"2025-07-28","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.129749768303985,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"508943e4-e9e1-4d10-9c0e-a7650e9d7315","model_name":"EXAONE 4.5 33B","obs_id":"artificial_analysis:humanitys-last-exam:508943e4-e9e1-4d10-9c0e-a7650e9d7315","organization":"LG AI Research","rank_in_source_response":206,"raw_value":"0.128822984244671","reported_by":"third_party","reported_date":"2026-04-09","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.128822984244671,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"cbac8c35-e069-4c73-823e-0953e6ed0e85","model_name":"Qwen3 Max Thinking (Preview)","obs_id":"artificial_analysis:humanitys-last-exam:cbac8c35-e069-4c73-823e-0953e6ed0e85","organization":"Qwen","rank_in_source_response":207,"raw_value":"0.126506024096386","reported_by":"third_party","reported_date":"2025-11-03","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.126506024096386,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"c8a79180-7d16-4474-8701-9a77c0baa56a","model_name":"Qwen3 Next 80B A3B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:c8a79180-7d16-4474-8701-9a77c0baa56a","organization":"Qwen","rank_in_source_response":208,"raw_value":"0.125579240037071","reported_by":"third_party","reported_date":"2025-09-11","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.125579240037071,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"ccbfa8c3-a762-480b-aade-34fb9697f98c","model_name":"Claude 4.1 Opus (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:ccbfa8c3-a762-480b-aade-34fb9697f98c","organization":"Anthropic","rank_in_source_response":209,"raw_value":"0.124652455977757","reported_by":"third_party","reported_date":"2025-08-05","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.124652455977757,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"8a4a5ead-7789-4389-8400-30e9d20370b7","model_name":"Claude 4 Opus (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:8a4a5ead-7789-4389-8400-30e9d20370b7","organization":"Anthropic","rank_in_source_response":210,"raw_value":"0.123262279888786","reported_by":"third_party","reported_date":"2025-05-22","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.123262279888786,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"219ed587-60c5-4a48-9517-8480e08d0ca1","model_name":"Gemini 2.5 Flash (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:219ed587-60c5-4a48-9517-8480e08d0ca1","organization":"Google","rank_in_source_response":211,"raw_value":"0.121408711770158","reported_by":"third_party","reported_date":"2025-05-20","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.121408711770158,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"353c92f3-2148-4c2d-9231-aa7e1322a1fd","model_name":"Qwen3.8 27B (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:353c92f3-2148-4c2d-9231-aa7e1322a1fd","organization":"Qwen","rank_in_source_response":211,"raw_value":"0.121408711770158","reported_by":"third_party","reported_date":"2026-08-14","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.121408711770158,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"ac1031bc-c53e-4af7-9c6e-2005e0ff44fa","model_name":"Apriel-v1.5-15B-Thinker","obs_id":"artificial_analysis:humanitys-last-exam:ac1031bc-c53e-4af7-9c6e-2005e0ff44fa","organization":"ServiceNow","rank_in_source_response":211,"raw_value":"0.121408711770158","reported_by":"third_party","reported_date":"2025-09-30","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.121408711770158,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"68c89ebf-779c-4445-9241-de964cd17355","model_name":"Gemini 2.5 Flash Preview (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:68c89ebf-779c-4445-9241-de964cd17355","organization":"Google","rank_in_source_response":214,"raw_value":"0.121","reported_by":"third_party","reported_date":"2025-04-17","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.121,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"076f2674-bc4b-4925-be59-50832eb8c090","model_name":"o3-mini (high)","obs_id":"artificial_analysis:humanitys-last-exam:076f2674-bc4b-4925-be59-50832eb8c090","organization":"OpenAI","rank_in_source_response":215,"raw_value":"0.1204","reported_by":"third_party","reported_date":"2025-01-31","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.1204,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"9815da7d-70f4-44d6-b539-9ffef0faa152","model_name":"Nemotron Cascade 2 30B A3B","obs_id":"artificial_analysis:humanitys-last-exam:9815da7d-70f4-44d6-b539-9ffef0faa152","organization":"NVIDIA","rank_in_source_response":216,"raw_value":"0.120018535681186","reported_by":"third_party","reported_date":"2026-03-19","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.120018535681186,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"ea5d2c10-1051-437d-95c2-18d5e4d14ff3","model_name":"Cogito v2.1 (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:ea5d2c10-1051-437d-95c2-18d5e4d14ff3","organization":"Deep Cogito","rank_in_source_response":216,"raw_value":"0.120018535681186","reported_by":"third_party","reported_date":"2025-11-18","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.120018535681186,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e","model_name":"Command A+","obs_id":"artificial_analysis:humanitys-last-exam:2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e","organization":"Cohere","rank_in_source_response":218,"raw_value":"0.119555143651529","reported_by":"third_party","reported_date":"2026-05-20","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.119555143651529,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"7ae943a9-9310-4472-a834-c61f0ab68485","model_name":"Qwen3 Max","obs_id":"artificial_analysis:humanitys-last-exam:7ae943a9-9310-4472-a834-c61f0ab68485","organization":"Qwen","rank_in_source_response":219,"raw_value":"0.119091751621872","reported_by":"third_party","reported_date":"2025-09-23","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.119091751621872,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"a803d3d0-d22e-49a0-ac2c-b9c6f1141065","model_name":"Qwen3 VL 235B A22B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:a803d3d0-d22e-49a0-ac2c-b9c6f1141065","organization":"Qwen","rank_in_source_response":219,"raw_value":"0.119091751621872","reported_by":"third_party","reported_date":"2025-09-23","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.119091751621872,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"d0aa27aa-4705-4184-9a1d-483b78c9331c","model_name":"Gemma 4 31B (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:d0aa27aa-4705-4184-9a1d-483b78c9331c","organization":"Google","rank_in_source_response":221,"raw_value":"0.118164967562558","reported_by":"third_party","reported_date":"2026-04-02","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.118164967562558,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"61bd9367-e520-4ec8-989e-5fbf50e61610","model_name":"Nova 2.0 Lite (high)","obs_id":"artificial_analysis:humanitys-last-exam:61bd9367-e520-4ec8-989e-5fbf50e61610","organization":"Amazon","rank_in_source_response":222,"raw_value":"0.11631139944393","reported_by":"third_party","reported_date":"2025-10-29","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.11631139944393,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"70882ec6-914c-41f0-9754-5e8f75005f77","model_name":"Gemma 4 26B A4B (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:70882ec6-914c-41f0-9754-5e8f75005f77","organization":"Google","rank_in_source_response":223,"raw_value":"0.114921223354958","reported_by":"third_party","reported_date":"2026-04-02","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.114921223354958,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"44b19b51-5367-4ef9-a2ff-2f90b89a0867","model_name":"EXAONE 4.0 32B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:44b19b51-5367-4ef9-a2ff-2f90b89a0867","organization":"LG AI Research","rank_in_source_response":224,"raw_value":"0.114457831325301","reported_by":"third_party","reported_date":"2025-07-15","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.114457831325301,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"76dcf6ef-39ea-4be0-b693-b88da25b4caf","model_name":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:76dcf6ef-39ea-4be0-b693-b88da25b4caf","organization":"NVIDIA","rank_in_source_response":225,"raw_value":"0.113994439295644","reported_by":"third_party","reported_date":"2025-12-15","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.113994439295644,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"9b97a35e-6ac7-44d9-91c6-422fa678963e","model_name":"GPT-5.6 Terra (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:9b97a35e-6ac7-44d9-91c6-422fa678963e","organization":"OpenAI","rank_in_source_response":225,"raw_value":"0.113994439295644","reported_by":"third_party","reported_date":"2026-07-09","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.113994439295644,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"493f6a1e-7717-4e98-9d6f-548b92c4702d","model_name":"GPT-5.4 (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:493f6a1e-7717-4e98-9d6f-548b92c4702d","organization":"OpenAI","rank_in_source_response":227,"raw_value":"0.112604263206673","reported_by":"third_party","reported_date":"2026-03-05","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.112604263206673,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"6d9a176d-feb8-4dac-8872-afe32b31897f","model_name":"DeepSeek V3.2 (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:6d9a176d-feb8-4dac-8872-afe32b31897f","organization":"DeepSeek","rank_in_source_response":228,"raw_value":"0.112140871177016","reported_by":"third_party","reported_date":"2025-12-01","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.112140871177016,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"f2e21112-192e-4aed-ae82-68ca3b38e667","model_name":"Claude Sonnet 4.6 (Non-reasoning, Low Effort)","obs_id":"artificial_analysis:humanitys-last-exam:f2e21112-192e-4aed-ae82-68ca3b38e667","organization":"Anthropic","rank_in_source_response":228,"raw_value":"0.112140871177016","reported_by":"third_party","reported_date":"2026-02-17","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.112140871177016,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"3373245b-e6dc-4b66-a7b0-3f06f9b7bd46","model_name":"Qwen3 235B A22B 2507 Instruct","obs_id":"artificial_analysis:humanitys-last-exam:3373245b-e6dc-4b66-a7b0-3f06f9b7bd46","organization":"Qwen","rank_in_source_response":230,"raw_value":"0.111214087117702","reported_by":"third_party","reported_date":"2025-07-21","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.111214087117702,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"a29e66d6-1c3c-456a-8770-59ee3845b35d","model_name":"Ring-1T","obs_id":"artificial_analysis:humanitys-last-exam:a29e66d6-1c3c-456a-8770-59ee3845b35d","organization":"InclusionAI","rank_in_source_response":230,"raw_value":"0.111214087117702","reported_by":"third_party","reported_date":"2025-10-13","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.111214087117702,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"1e9907e0-ffac-4595-b006-962e4f1da7cf","model_name":"North Mini Code","obs_id":"artificial_analysis:humanitys-last-exam:1e9907e0-ffac-4595-b006-962e4f1da7cf","organization":"Cohere","rank_in_source_response":232,"raw_value":"0.110750695088044","reported_by":"third_party","reported_date":"2026-06-09","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.110750695088044,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"45790612-02e3-4c42-b5bd-cd7ed2ea1f2f","model_name":"Sarvam 105B (high)","obs_id":"artificial_analysis:humanitys-last-exam:45790612-02e3-4c42-b5bd-cd7ed2ea1f2f","organization":"Sarvam","rank_in_source_response":233,"raw_value":"0.110287303058387","reported_by":"third_party","reported_date":"2026-03-06","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.110287303058387,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"ff9bc5e5-a02f-4270-983e-4b3f834f3363","model_name":"Grok 3 mini Reasoning (high)","obs_id":"artificial_analysis:humanitys-last-exam:ff9bc5e5-a02f-4270-983e-4b3f834f3363","organization":"xAI","rank_in_source_response":234,"raw_value":"0.1101","reported_by":"third_party","reported_date":"2025-02-19","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.1101,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"36f73aaf-d38a-4b56-a2b3-d04d17186910","model_name":"gpt-oss-20b (high)","obs_id":"artificial_analysis:humanitys-last-exam:36f73aaf-d38a-4b56-a2b3-d04d17186910","organization":"OpenAI","rank_in_source_response":235,"raw_value":"0.10982391102873","reported_by":"third_party","reported_date":"2025-08-05","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.10982391102873,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"c76e0ae8-0fd2-45c0-a39d-d398fce9b128","model_name":"Falcon-H1R-7B","obs_id":"artificial_analysis:humanitys-last-exam:c76e0ae8-0fd2-45c0-a39d-d398fce9b128","organization":"TII UAE","rank_in_source_response":235,"raw_value":"0.10982391102873","reported_by":"third_party","reported_date":"2026-01-04","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.10982391102873,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"bbe6d782-e630-48d5-b11c-3ce37f373f1e","model_name":"Qwen3 235B A22B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:bbe6d782-e630-48d5-b11c-3ce37f373f1e","organization":"Qwen","rank_in_source_response":237,"raw_value":"0.1098","reported_by":"third_party","reported_date":"2025-04-28","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.1098,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"7d73161f-002f-4c9c-b4f8-6c4d91f2ba8e","model_name":"Nanbeige4.1-3B","obs_id":"artificial_analysis:humanitys-last-exam:7d73161f-002f-4c9c-b4f8-6c4d91f2ba8e","organization":"Nanbeige","rank_in_source_response":238,"raw_value":"0.108897126969416","reported_by":"third_party","reported_date":"2026-02-11","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.108897126969416,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"82b207dd-d285-4a52-b2fc-2cbd27543899","model_name":"Hermes 4 - Llama-3.1 405B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:82b207dd-d285-4a52-b2fc-2cbd27543899","organization":"Nous Research","rank_in_source_response":238,"raw_value":"0.108897126969416","reported_by":"third_party","reported_date":"2025-08-27","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.108897126969416,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"acad0665-9457-4531-abd5-b59efd7a89ea","model_name":"Step3 VL 10B","obs_id":"artificial_analysis:humanitys-last-exam:acad0665-9457-4531-abd5-b59efd7a89ea","organization":"StepFun","rank_in_source_response":240,"raw_value":"0.108433734939759","reported_by":"third_party","reported_date":"2026-01-20","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.108433734939759,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"c3f12f61-9d57-4e2c-9106-5a82bb1cfee2","model_name":"DiffusionGemma 26B A4B","obs_id":"artificial_analysis:humanitys-last-exam:c3f12f61-9d57-4e2c-9106-5a82bb1cfee2","organization":"Google","rank_in_source_response":240,"raw_value":"0.108433734939759","reported_by":"third_party","reported_date":"2026-06-10","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.108433734939759,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"a71c1a35-ccc8-43f0-a5a2-070a690b9a00","model_name":"Apriel-v1.6-15B-Thinker","obs_id":"artificial_analysis:humanitys-last-exam:a71c1a35-ccc8-43f0-a5a2-070a690b9a00","organization":"ServiceNow","rank_in_source_response":242,"raw_value":"0.107970342910102","reported_by":"third_party","reported_date":"2025-11-25","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.107970342910102,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"a7564055-f8ba-4c4b-9e2d-060f61263645","model_name":"Claude 4 Sonnet (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:a7564055-f8ba-4c4b-9e2d-060f61263645","organization":"Anthropic","rank_in_source_response":243,"raw_value":"0.107043558850788","reported_by":"third_party","reported_date":"2025-05-22","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.107043558850788,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"29976311-665a-4b2f-ac72-557c33e0758e","model_name":"Nemotron 3.5 Lightning","obs_id":"artificial_analysis:humanitys-last-exam:29976311-665a-4b2f-ac72-557c33e0758e","organization":"NVIDIA","rank_in_source_response":244,"raw_value":"0.105653382761817","reported_by":"third_party","reported_date":"2026-08-11","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.105653382761817,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"a38d719a-709c-4983-b3e7-7090389ae9a6","model_name":"K2-V2 (high)","obs_id":"artificial_analysis:humanitys-last-exam:a38d719a-709c-4983-b3e7-7090389ae9a6","organization":"MBZUAI Institute of Foundation Models","rank_in_source_response":245,"raw_value":"0.105189990732159","reported_by":"third_party","reported_date":"2025-12-05","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.105189990732159,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"59a1bb20-9170-4dc2-ba9c-12d326cf068e","model_name":"Solar Open 100B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:59a1bb20-9170-4dc2-ba9c-12d326cf068e","organization":"Upstage","rank_in_source_response":246,"raw_value":"0.104263206672845","reported_by":"third_party","reported_date":"2025-12-17","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.104263206672845,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"a6340098-d7ae-462d-b372-0a0a67fc44b4","model_name":"Claude 4.5 Haiku (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:a6340098-d7ae-462d-b372-0a0a67fc44b4","organization":"Anthropic","rank_in_source_response":247,"raw_value":"0.103799814643188","reported_by":"third_party","reported_date":"2025-10-15","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.103799814643188,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"5e0164b3-d902-4bcb-a1b2-83b4f4cd6143","model_name":"Qwen3 30B A3B 2507 (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:5e0164b3-d902-4bcb-a1b2-83b4f4cd6143","organization":"Qwen","rank_in_source_response":248,"raw_value":"0.102873030583874","reported_by":"third_party","reported_date":"2025-07-30","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.102873030583874,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"864da2a5-156c-45fd-873c-8923be91914f","model_name":"Magistral Medium 1.2","obs_id":"artificial_analysis:humanitys-last-exam:864da2a5-156c-45fd-873c-8923be91914f","organization":"Mistral","rank_in_source_response":248,"raw_value":"0.102873030583874","reported_by":"third_party","reported_date":"2025-09-18","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.102873030583874,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"b89c4faf-219e-4171-a1aa-e3bd2fd0a924","model_name":"Solar Pro 3","obs_id":"artificial_analysis:humanitys-last-exam:b89c4faf-219e-4171-a1aa-e3bd2fd0a924","organization":"Upstage","rank_in_source_response":248,"raw_value":"0.102873030583874","reported_by":"third_party","reported_date":"2026-04-06","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.102873030583874,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"5b2beb12-81a9-47a1-8a2a-d0a727185b50","model_name":"Qwen3 Max (Preview)","obs_id":"artificial_analysis:humanitys-last-exam:5b2beb12-81a9-47a1-8a2a-d0a727185b50","organization":"Qwen","rank_in_source_response":251,"raw_value":"0.101482854494903","reported_by":"third_party","reported_date":"2025-09-05","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.101482854494903,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"d370fcbf-c4a1-41a2-abc4-d204fcc3fcbf","model_name":"Qwen3 VL 32B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:d370fcbf-c4a1-41a2-abc4-d204fcc3fcbf","organization":"Qwen","rank_in_source_response":251,"raw_value":"0.101482854494903","reported_by":"third_party","reported_date":"2025-10-21","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.101482854494903,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"fc92f822-04b7-420d-9c07-a21af5e9aac7","model_name":"Qwen3 Coder Next","obs_id":"artificial_analysis:humanitys-last-exam:fc92f822-04b7-420d-9c07-a21af5e9aac7","organization":"Qwen","rank_in_source_response":251,"raw_value":"0.101482854494903","reported_by":"third_party","reported_date":"2026-02-03","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.101482854494903,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"5a49ef80-3af5-404b-8ac0-e1b230ae95de","model_name":"K2 Think V2","obs_id":"artificial_analysis:humanitys-last-exam:5a49ef80-3af5-404b-8ac0-e1b230ae95de","organization":"MBZUAI Institute of Foundation Models","rank_in_source_response":254,"raw_value":"0.101019462465246","reported_by":"third_party","reported_date":"2025-12-15","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.101019462465246,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"651ef7ae-9a8f-477e-9c8e-460aa156ba02","model_name":"Qwen3.5 4B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:651ef7ae-9a8f-477e-9c8e-460aa156ba02","organization":"Qwen","rank_in_source_response":255,"raw_value":"0.0991658943466172","reported_by":"third_party","reported_date":"2026-03-02","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0991658943466172,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"3fd96175-4ef1-434c-8795-f873aec2abc1","model_name":"Mistral Small 4 (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:3fd96175-4ef1-434c-8795-f873aec2abc1","organization":"Mistral","rank_in_source_response":256,"raw_value":"0.0987025023169602","reported_by":"third_party","reported_date":"2026-03-16","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0987025023169602,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"5c6533f3-75a2-4109-b9a9-3623afc6b86a","model_name":"Seed-OSS-36B-Instruct","obs_id":"artificial_analysis:humanitys-last-exam:5c6533f3-75a2-4109-b9a9-3623afc6b86a","organization":"ByteDance Seed","rank_in_source_response":256,"raw_value":"0.0987025023169602","reported_by":"third_party","reported_date":"2025-08-20","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0987025023169602,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"660965b2-66d2-49ee-a6b9-79a6ac47d3c0","model_name":"Magistral Medium 1","obs_id":"artificial_analysis:humanitys-last-exam:660965b2-66d2-49ee-a6b9-79a6ac47d3c0","organization":"Mistral","rank_in_source_response":258,"raw_value":"0.0982391102873031","reported_by":"third_party","reported_date":"2025-06-10","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0982391102873031,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"e8aa417f-18fe-46b0-ba62-ef99785a9585","model_name":"GLM-5.2 (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:e8aa417f-18fe-46b0-ba62-ef99785a9585","organization":"Z.ai","rank_in_source_response":259,"raw_value":"0.097775718257646","reported_by":"third_party","reported_date":"2026-06-16","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.097775718257646,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"13358187-4584-479c-ab43-5bcdf8f297a4","model_name":"Claude 3.7 Sonnet (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:13358187-4584-479c-ab43-5bcdf8f297a4","organization":"Anthropic","rank_in_source_response":260,"raw_value":"0.0967","reported_by":"third_party","reported_date":"2025-02-24","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0967,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"47b7df55-5804-40de-ba11-317de786710a","model_name":"Ring-flash-2.0","obs_id":"artificial_analysis:humanitys-last-exam:47b7df55-5804-40de-ba11-317de786710a","organization":"InclusionAI","rank_in_source_response":261,"raw_value":"0.0963855421686747","reported_by":"third_party","reported_date":"2025-09-19","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0963855421686747,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"d2d7dd95-770f-4cb0-9bbc-d275ac19c265","model_name":"GLM-4.6V (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:d2d7dd95-770f-4cb0-9bbc-d275ac19c265","organization":"Z.ai","rank_in_source_response":261,"raw_value":"0.0963855421686747","reported_by":"third_party","reported_date":"2025-12-08","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0963855421686747,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"e18e5e6a-5a31-4c0b-b80b-ac401392f446","model_name":"GPT-5 nano (high)","obs_id":"artificial_analysis:humanitys-last-exam:e18e5e6a-5a31-4c0b-b80b-ac401392f446","organization":"OpenAI","rank_in_source_response":263,"raw_value":"0.0949953660797034","reported_by":"third_party","reported_date":"2025-08-07","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0949953660797034,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"0d94dc87-12c8-4d4a-8d99-804ce3f17bc2","model_name":"Nova 2.0 Pro Preview (medium)","obs_id":"artificial_analysis:humanitys-last-exam:0d94dc87-12c8-4d4a-8d99-804ce3f17bc2","organization":"Amazon","rank_in_source_response":264,"raw_value":"0.0940685820203892","reported_by":"third_party","reported_date":"2025-11-27","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0940685820203892,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"20da3b31-fc0a-4359-abec-d59367bf1d9f","model_name":"Qwen3.5 9B (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:20da3b31-fc0a-4359-abec-d59367bf1d9f","organization":"Qwen","rank_in_source_response":265,"raw_value":"0.0936051899907322","reported_by":"third_party","reported_date":"2026-03-02","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0936051899907322,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"7eaf926c-5f39-4e58-ae50-c38b5fc630fc","model_name":"Ling 3.0 Tiny","obs_id":"artificial_analysis:humanitys-last-exam:7eaf926c-5f39-4e58-ae50-c38b5fc630fc","organization":"InclusionAI","rank_in_source_response":266,"raw_value":"0.0931417979610751","reported_by":"third_party","reported_date":"2026-08-06","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0931417979610751,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"e0099b99-d368-4562-b0de-4016ea58af54","model_name":"Mi:dm K 2.5 Pro Preview","obs_id":"artificial_analysis:humanitys-last-exam:e0099b99-d368-4562-b0de-4016ea58af54","organization":"Korea Telecom","rank_in_source_response":267,"raw_value":"0.0908248378127896","reported_by":"third_party","reported_date":"2025-12-11","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0908248378127896,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"07c35e00-2b12-44c8-91cc-408629cd569e","model_name":"DeepSeek V3.2 Exp (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:07c35e00-2b12-44c8-91cc-408629cd569e","organization":"DeepSeek","rank_in_source_response":268,"raw_value":"0.0903614457831325","reported_by":"third_party","reported_date":"2025-09-29","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0903614457831325,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"fbdf8da1-b341-448c-b3cb-8aff1d8f70b9","model_name":"Nova 2.0 Lite (medium)","obs_id":"artificial_analysis:humanitys-last-exam:fbdf8da1-b341-448c-b3cb-8aff1d8f70b9","organization":"Amazon","rank_in_source_response":269,"raw_value":"0.0898980537534754","reported_by":"third_party","reported_date":"2025-10-29","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0898980537534754,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"ce3d286e-093d-413d-a81a-0270309f039e","model_name":"Qwen3 VL 30B A3B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:ce3d286e-093d-413d-a81a-0270309f039e","organization":"Qwen","rank_in_source_response":270,"raw_value":"0.0894346617238184","reported_by":"third_party","reported_date":"2025-10-03","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0894346617238184,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"9ca246a7-cf13-42c9-9182-5b5ad6b79026","model_name":"MiniMax M1 80k","obs_id":"artificial_analysis:humanitys-last-exam:9ca246a7-cf13-42c9-9182-5b5ad6b79026","organization":"MiniMax","rank_in_source_response":271,"raw_value":"0.0889712696941613","reported_by":"third_party","reported_date":"2025-06-17","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0889712696941613,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"666eb13f-0d22-4438-8eb0-01876e1a8604","model_name":"Motif-2-12.7B-Reasoning","obs_id":"artificial_analysis:humanitys-last-exam:666eb13f-0d22-4438-8eb0-01876e1a8604","organization":"Motif Technologies","rank_in_source_response":272,"raw_value":"0.08758109360519","reported_by":"third_party","reported_date":"2025-12-04","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.08758109360519,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"6ba9e8eb-8124-436d-842f-dbe36df80c27","model_name":"Hermes 4 - Llama-3.1 70B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:6ba9e8eb-8124-436d-842f-dbe36df80c27","organization":"Nous Research","rank_in_source_response":272,"raw_value":"0.08758109360519","reported_by":"third_party","reported_date":"2025-08-27","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.08758109360519,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"2e46d2fd-eb2b-42b9-9fe4-be50630fe870","model_name":"Ling-2.6-1T","obs_id":"artificial_analysis:humanitys-last-exam:2e46d2fd-eb2b-42b9-9fe4-be50630fe870","organization":"InclusionAI","rank_in_source_response":274,"raw_value":"0.0871177015755329","reported_by":"third_party","reported_date":"2026-04-23","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0871177015755329,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"877fdfc9-2026-477a-af96-e4fd602c0131","model_name":"Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:877fdfc9-2026-477a-af96-e4fd602c0131","organization":"Google","rank_in_source_response":274,"raw_value":"0.0871177015755329","reported_by":"third_party","reported_date":"2025-09-25","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0871177015755329,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"8eb02396-f231-4189-ae15-05f7facebd9b","model_name":"GPT-5 nano (medium)","obs_id":"artificial_analysis:humanitys-last-exam:8eb02396-f231-4189-ae15-05f7facebd9b","organization":"OpenAI","rank_in_source_response":274,"raw_value":"0.0871177015755329","reported_by":"third_party","reported_date":"2025-08-07","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0871177015755329,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"dfb9292d-bc7c-4425-a260-4256217e709f","model_name":"DeepSeek V3.1 Terminus (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:dfb9292d-bc7c-4425-a260-4256217e709f","organization":"DeepSeek","rank_in_source_response":277,"raw_value":"0.0866543095458758","reported_by":"third_party","reported_date":"2025-09-22","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0866543095458758,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"82b36b4d-84dd-4bc0-ad32-e3aee9442789","model_name":"MiMo-V2-Flash (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:82b36b4d-84dd-4bc0-ad32-e3aee9442789","organization":"Xiaomi","rank_in_source_response":278,"raw_value":"0.0857275254865616","reported_by":"third_party","reported_date":"2025-12-16","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0857275254865616,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"0e34f05c-387e-4968-be15-ccec4a55d8c1","model_name":"DeepSeek R1 (Jan '25)","obs_id":"artificial_analysis:humanitys-last-exam:0e34f05c-387e-4968-be15-ccec4a55d8c1","organization":"DeepSeek","rank_in_source_response":279,"raw_value":"0.085","reported_by":"third_party","reported_date":"2025-01-20","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.085,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"6e2a2572-ed8d-4616-8d7d-68d125fc8ee7","model_name":"DeepSeek V4 Pro (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:6e2a2572-ed8d-4616-8d7d-68d125fc8ee7","organization":"DeepSeek","rank_in_source_response":280,"raw_value":"0.082483781278962","reported_by":"third_party","reported_date":"2026-04-24","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.082483781278962,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"df4c5a29-4b5c-4fef-9f7f-5e24e118ab65","model_name":"Mi:dm K 2.5 Pro","obs_id":"artificial_analysis:humanitys-last-exam:df4c5a29-4b5c-4fef-9f7f-5e24e118ab65","organization":"Korea Telecom","rank_in_source_response":281,"raw_value":"0.0806302131603336","reported_by":"third_party","reported_date":"2025-12-11","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0806302131603336,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"6dd8ba55-5680-44a9-b309-82928165d5f0","model_name":"GPT-5.2 (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:6dd8ba55-5680-44a9-b309-82928165d5f0","organization":"OpenAI","rank_in_source_response":282,"raw_value":"0.0801668211306766","reported_by":"third_party","reported_date":"2025-12-11","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0801668211306766,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"a06bd3fc-86db-4a8e-ae6d-7459444d08c9","model_name":"Grok Code Fast 1","obs_id":"artificial_analysis:humanitys-last-exam:a06bd3fc-86db-4a8e-ae6d-7459444d08c9","organization":"xAI","rank_in_source_response":282,"raw_value":"0.0801668211306766","reported_by":"third_party","reported_date":"2025-08-28","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0801668211306766,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"30c9ba61-d0a1-4794-938e-35865f379d15","model_name":"Qwen3.5 4B (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:30c9ba61-d0a1-4794-938e-35865f379d15","organization":"Qwen","rank_in_source_response":284,"raw_value":"0.0797034291010195","reported_by":"third_party","reported_date":"2026-03-02","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0797034291010195,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"2dad8957-4c16-4e74-bf2d-8b21514e0ae9","model_name":"o3-mini","obs_id":"artificial_analysis:humanitys-last-exam:2dad8957-4c16-4e74-bf2d-8b21514e0ae9","organization":"OpenAI","rank_in_source_response":285,"raw_value":"0.0791","reported_by":"third_party","reported_date":"2025-01-31","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0791,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"385376b1-9815-47dd-83cc-85aac34f247d","model_name":"MiniMax M1 40k","obs_id":"artificial_analysis:humanitys-last-exam:385376b1-9815-47dd-83cc-85aac34f247d","organization":"MiniMax","rank_in_source_response":286,"raw_value":"0.0783132530120482","reported_by":"third_party","reported_date":"2025-06-17","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0783132530120482,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"ad173c8d-f14f-4230-90e9-60979b7720e7","model_name":"DeepSeek V4 Flash (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:ad173c8d-f14f-4230-90e9-60979b7720e7","organization":"DeepSeek","rank_in_source_response":287,"raw_value":"0.0778498609823911","reported_by":"third_party","reported_date":"2026-04-24","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0778498609823911,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"2698f6c6-e436-47ce-a583-dbc25596c571","model_name":"Qwen3 Next 80B A3B Instruct","obs_id":"artificial_analysis:humanitys-last-exam:2698f6c6-e436-47ce-a583-dbc25596c571","organization":"Qwen","rank_in_source_response":288,"raw_value":"0.0764596848934198","reported_by":"third_party","reported_date":"2025-09-11","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0764596848934198,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"f164b41f-44c5-4675-bca3-fea1db4bd9ae","model_name":"GLM-5 (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:f164b41f-44c5-4675-bca3-fea1db4bd9ae","organization":"Z.ai","rank_in_source_response":288,"raw_value":"0.0764596848934198","reported_by":"third_party","reported_date":"2026-02-11","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0764596848934198,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"2c4394a2-b443-470a-908e-5c4a271b780c","model_name":"GLM-4.7-Flash (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:2c4394a2-b443-470a-908e-5c4a271b780c","organization":"Z.ai","rank_in_source_response":290,"raw_value":"0.0759962928637627","reported_by":"third_party","reported_date":"2026-01-19","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0759962928637627,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"6f3534b1-1168-472e-b3e3-23ab521504f5","model_name":"Qwen3.5 Omni Flash","obs_id":"artificial_analysis:humanitys-last-exam:6f3534b1-1168-472e-b3e3-23ab521504f5","organization":"Qwen","rank_in_source_response":290,"raw_value":"0.0759962928637627","reported_by":"third_party","reported_date":"2026-03-30","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0759962928637627,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"0fec07d5-a9b2-407a-b5f8-5bf10bd86b59","model_name":"Magistral Small 1","obs_id":"artificial_analysis:humanitys-last-exam:0fec07d5-a9b2-407a-b5f8-5bf10bd86b59","organization":"Mistral","rank_in_source_response":292,"raw_value":"0.0755329008341057","reported_by":"third_party","reported_date":"2025-06-10","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0755329008341057,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"764dd095-6ebd-4760-8eb3-cbc40964db2e","model_name":"Sarvam 30B (high)","obs_id":"artificial_analysis:humanitys-last-exam:764dd095-6ebd-4760-8eb3-cbc40964db2e","organization":"Sarvam","rank_in_source_response":293,"raw_value":"0.0750695088044486","reported_by":"third_party","reported_date":"2026-03-06","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0750695088044486,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"b97ef678-2d31-4375-9416-67ea97f87204","model_name":"Qwen3 Omni 30B A3B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:b97ef678-2d31-4375-9416-67ea97f87204","organization":"Qwen","rank_in_source_response":294,"raw_value":"0.0746061167747915","reported_by":"third_party","reported_date":"2025-09-22","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0746061167747915,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"441734a9-8901-4850-9bae-b474c370291f","model_name":"Kimi K2","obs_id":"artificial_analysis:humanitys-last-exam:441734a9-8901-4850-9bae-b474c370291f","organization":"Moonshot AI","rank_in_source_response":295,"raw_value":"0.0741427247451344","reported_by":"third_party","reported_date":"2025-07-11","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0741427247451344,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"b00ecd62-a53f-4aed-b833-3e9d6b0170ba","model_name":"Qwen3 32B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:b00ecd62-a53f-4aed-b833-3e9d6b0170ba","organization":"Qwen","rank_in_source_response":296,"raw_value":"0.0741","reported_by":"third_party","reported_date":"2025-04-28","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0741,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"cf095603-72b6-47f8-8ee1-09a42890f92a","model_name":"Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:cf095603-72b6-47f8-8ee1-09a42890f92a","organization":"NVIDIA","rank_in_source_response":297,"raw_value":"0.0738","reported_by":"third_party","reported_date":"2025-04-07","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0738,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"eb689f7a-f210-4a87-b407-f249897f2764","model_name":"Solar Pro 2 (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:eb689f7a-f210-4a87-b407-f249897f2764","organization":"Upstage","rank_in_source_response":298,"raw_value":"0.0736793327154773","reported_by":"third_party","reported_date":"2025-07-09","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0736793327154773,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"ceb4d610-d0a4-48c1-bea0-80ed76f1e5ca","model_name":"QwQ 32B","obs_id":"artificial_analysis:humanitys-last-exam:ceb4d610-d0a4-48c1-bea0-80ed76f1e5ca","organization":"Qwen","rank_in_source_response":299,"raw_value":"0.0735","reported_by":"third_party","reported_date":"2025-03-05","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0735,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"15b56b8e-7b93-4ed9-ac06-75c922e3b86e","model_name":"Ling-1T","obs_id":"artificial_analysis:humanitys-last-exam:15b56b8e-7b93-4ed9-ac06-75c922e3b86e","organization":"InclusionAI","rank_in_source_response":300,"raw_value":"0.0732159406858202","reported_by":"third_party","reported_date":"2025-10-08","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0732159406858202,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"e1cfa926-9e2b-4a0d-8c31-48366a5041c5","model_name":"Llama Nemotron Super 49B v1.5 (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:e1cfa926-9e2b-4a0d-8c31-48366a5041c5","organization":"NVIDIA","rank_in_source_response":300,"raw_value":"0.0732159406858202","reported_by":"third_party","reported_date":"2025-07-25","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0732159406858202,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"91cb6144-4937-4e4e-aeda-b4341d355c10","model_name":"Claude 4.5 Sonnet (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:91cb6144-4937-4e4e-aeda-b4341d355c10","organization":"Anthropic","rank_in_source_response":302,"raw_value":"0.072289156626506","reported_by":"third_party","reported_date":"2025-09-29","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.072289156626506,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"dc64f856-3ded-497d-9527-d41d31267ed5","model_name":"GPT-5.6 Luna (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:dc64f856-3ded-497d-9527-d41d31267ed5","organization":"OpenAI","rank_in_source_response":302,"raw_value":"0.072289156626506","reported_by":"third_party","reported_date":"2026-07-09","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.072289156626506,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"5d303dc9-c027-401f-9803-4e9aa3331007","model_name":"GLM-4.5-Air","obs_id":"artificial_analysis:humanitys-last-exam:5d303dc9-c027-401f-9803-4e9aa3331007","organization":"Z.ai","rank_in_source_response":304,"raw_value":"0.0704355885078777","reported_by":"third_party","reported_date":"2025-07-28","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0704355885078777,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"5ad2f60f-ee05-49fd-85a0-cef69aa7cb7b","model_name":"o1","obs_id":"artificial_analysis:humanitys-last-exam:5ad2f60f-ee05-49fd-85a0-cef69aa7cb7b","organization":"OpenAI","rank_in_source_response":305,"raw_value":"0.0701","reported_by":"third_party","reported_date":"2024-12-05","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0701,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"018c60e8-e908-431a-ba57-c840b1df3987","model_name":"Nova 2.0 Omni (medium)","obs_id":"artificial_analysis:humanitys-last-exam:018c60e8-e908-431a-ba57-c840b1df3987","organization":"Amazon","rank_in_source_response":306,"raw_value":"0.0695088044485635","reported_by":"third_party","reported_date":"2025-11-26","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0695088044485635,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"84922739-425f-46e1-87ac-bb4268dcacbb","model_name":"Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:84922739-425f-46e1-87ac-bb4268dcacbb","organization":"Google","rank_in_source_response":306,"raw_value":"0.0695088044485635","reported_by":"third_party","reported_date":"2025-09-08","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0695088044485635,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"b58b8272-cd3f-44b9-9b68-612f40779ce2","model_name":"Hy3-preview (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:b58b8272-cd3f-44b9-9b68-612f40779ce2","organization":"Tencent","rank_in_source_response":306,"raw_value":"0.0695088044485635","reported_by":"third_party","reported_date":"2026-04-23","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0695088044485635,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"7ec1065a-c90e-41e4-bd17-abb7042eed76","model_name":"Qwen3 30B A3B 2507 Instruct","obs_id":"artificial_analysis:humanitys-last-exam:7ec1065a-c90e-41e4-bd17-abb7042eed76","organization":"Qwen","rank_in_source_response":309,"raw_value":"0.0690454124189064","reported_by":"third_party","reported_date":"2025-07-29","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0690454124189064,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"e2b664ca-7992-4de6-8839-4867f035c892","model_name":"LFM2.5-8B-A1B","obs_id":"artificial_analysis:humanitys-last-exam:e2b664ca-7992-4de6-8839-4867f035c892","organization":"Liquid AI","rank_in_source_response":310,"raw_value":"0.0685820203892493","reported_by":"third_party","reported_date":"2026-05-28","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0685820203892493,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"6da314d3-a984-4734-8f31-47dd32fb4699","model_name":"Qwen3 VL 32B Instruct","obs_id":"artificial_analysis:humanitys-last-exam:6da314d3-a984-4734-8f31-47dd32fb4699","organization":"Qwen","rank_in_source_response":311,"raw_value":"0.0681186283595922","reported_by":"third_party","reported_date":"2025-10-21","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0681186283595922,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"8014c311-fa23-4a4b-8485-8a864db8a113","model_name":"Celeris-1","obs_id":"artificial_analysis:humanitys-last-exam:8014c311-fa23-4a4b-8485-8a864db8a113","organization":"Celeris","rank_in_source_response":311,"raw_value":"0.0681186283595922","reported_by":"third_party","reported_date":"2026-07-24","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0681186283595922,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"f4e8194a-d0e6-48eb-92be-4307de5aeeec","model_name":"Gemini 2.5 Flash-Lite (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:f4e8194a-d0e6-48eb-92be-4307de5aeeec","organization":"Google","rank_in_source_response":311,"raw_value":"0.0681186283595922","reported_by":"third_party","reported_date":"2025-06-17","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0681186283595922,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"90c2a9cf-ad7e-4332-9be2-2fd1309833e2","model_name":"Grok 4.3 (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:90c2a9cf-ad7e-4332-9be2-2fd1309833e2","organization":"xAI","rank_in_source_response":314,"raw_value":"0.0676552363299351","reported_by":"third_party","reported_date":"2026-04-30","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0676552363299351,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"48194e0f-8226-4c57-8cb2-2a0fb68a84c9","model_name":"LFM2.5-1.2B-Instruct","obs_id":"artificial_analysis:humanitys-last-exam:48194e0f-8226-4c57-8cb2-2a0fb68a84c9","organization":"Liquid AI","rank_in_source_response":315,"raw_value":"0.067191844300278","reported_by":"third_party","reported_date":"2026-01-05","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.067191844300278,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"fb65266f-5a7d-403c-85d5-ccdf0d1ca838","model_name":"DeepSeek V3.1 (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:fb65266f-5a7d-403c-85d5-ccdf0d1ca838","organization":"DeepSeek","rank_in_source_response":316,"raw_value":"0.0667284522706209","reported_by":"third_party","reported_date":"2025-08-21","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0667284522706209,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"d58cf573-1bd3-4d1f-9182-5482a460f570","model_name":"Qwen3 VL 235B A22B Instruct","obs_id":"artificial_analysis:humanitys-last-exam:d58cf573-1bd3-4d1f-9182-5482a460f570","organization":"Qwen","rank_in_source_response":317,"raw_value":"0.0662650602409639","reported_by":"third_party","reported_date":"2025-09-23","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0662650602409639,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"eab1492c-b853-4852-aa71-06b0ec2481c1","model_name":"GPT-5 (ChatGPT)","obs_id":"artificial_analysis:humanitys-last-exam:eab1492c-b853-4852-aa71-06b0ec2481c1","organization":"OpenAI","rank_in_source_response":317,"raw_value":"0.0662650602409639","reported_by":"third_party","reported_date":"2025-08-07","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0662650602409639,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"3435db18-9227-45a5-8e79-9546b14b5aaa","model_name":"Sonar Pro","obs_id":"artificial_analysis:humanitys-last-exam:3435db18-9227-45a5-8e79-9546b14b5aaa","organization":"Perplexity","rank_in_source_response":319,"raw_value":"0.0655","reported_by":"third_party","reported_date":"2025-01-21","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0655,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"77f5ff8b-1536-474a-a337-e1bfd138d343","model_name":"MiniCPM5-1B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:77f5ff8b-1536-474a-a337-e1bfd138d343","organization":"OpenBMB","rank_in_source_response":320,"raw_value":"0.0648748841519926","reported_by":"third_party","reported_date":"2026-05-25","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0648748841519926,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"0121d27b-5b8a-4901-8684-80589cc6d40d","model_name":"JT-35B-Flash","obs_id":"artificial_analysis:humanitys-last-exam:0121d27b-5b8a-4901-8684-80589cc6d40d","organization":"China Mobile","rank_in_source_response":321,"raw_value":"0.0644114921223355","reported_by":"third_party","reported_date":"2026-05-14","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0644114921223355,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"3d4e7366-928c-4eff-a8b0-2919c7d334c9","model_name":"JT-MINI","obs_id":"artificial_analysis:humanitys-last-exam:3d4e7366-928c-4eff-a8b0-2919c7d334c9","organization":"China Mobile","rank_in_source_response":321,"raw_value":"0.0644114921223355","reported_by":"third_party","reported_date":"2026-04-15","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0644114921223355,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"70152cb0-fb36-4732-a925-89ef40994be1","model_name":"Magistral Small 1.2","obs_id":"artificial_analysis:humanitys-last-exam:70152cb0-fb36-4732-a925-89ef40994be1","organization":"Mistral","rank_in_source_response":321,"raw_value":"0.0644114921223355","reported_by":"third_party","reported_date":"2025-09-17","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0644114921223355,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"a68afa0b-7fe2-4e9d-bf3e-741cce3c6aeb","model_name":"Granite 4.0 H 350M","obs_id":"artificial_analysis:humanitys-last-exam:a68afa0b-7fe2-4e9d-bf3e-741cce3c6aeb","organization":"IBM","rank_in_source_response":321,"raw_value":"0.0644114921223355","reported_by":"third_party","reported_date":"2025-10-28","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0644114921223355,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"c8a3fa87-735e-49a9-afb1-270c5e9f53f7","model_name":"Olmo 3 32B Think","obs_id":"artificial_analysis:humanitys-last-exam:c8a3fa87-735e-49a9-afb1-270c5e9f53f7","organization":"Allen Institute for AI","rank_in_source_response":321,"raw_value":"0.0644114921223355","reported_by":"third_party","reported_date":"2025-11-20","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0644114921223355,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"66445f84-b2e3-4202-afdc-92ba0f0e5f36","model_name":"Kimi K2 0905","obs_id":"artificial_analysis:humanitys-last-exam:66445f84-b2e3-4202-afdc-92ba0f0e5f36","organization":"Moonshot AI","rank_in_source_response":326,"raw_value":"0.0639481000926784","reported_by":"third_party","reported_date":"2025-09-05","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0639481000926784,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"81b6ddfc-111e-4422-bd44-42ee6165b699","model_name":"GLM-4.7 (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:81b6ddfc-111e-4422-bd44-42ee6165b699","organization":"Z.ai","rank_in_source_response":326,"raw_value":"0.0639481000926784","reported_by":"third_party","reported_date":"2025-12-22","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0639481000926784,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"0399e614-5d46-484f-9183-e4f32d74e1c6","model_name":"Gemini 2.0 Flash Thinking Experimental (Jan '25)","obs_id":"artificial_analysis:humanitys-last-exam:0399e614-5d46-484f-9183-e4f32d74e1c6","organization":"Google","rank_in_source_response":328,"raw_value":"0.0635","reported_by":"third_party","reported_date":"2025-01-21","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0635,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"025ec6b6-df4a-449f-9a03-24e4388d6863","model_name":"Gemma 4 12B (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:025ec6b6-df4a-449f-9a03-24e4388d6863","organization":"Google","rank_in_source_response":329,"raw_value":"0.0634847080630213","reported_by":"third_party","reported_date":"2026-06-03","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0634847080630213,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"3068def4-7270-4c06-a320-6f6a5623d564","model_name":"GLM-4.5V (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:3068def4-7270-4c06-a320-6f6a5623d564","organization":"Z.ai","rank_in_source_response":330,"raw_value":"0.0630213160333642","reported_by":"third_party","reported_date":"2025-08-11","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0630213160333642,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"51d0b717-953d-4b44-af61-406c6b7dff39","model_name":"Qwen3 VL 30B A3B Instruct","obs_id":"artificial_analysis:humanitys-last-exam:51d0b717-953d-4b44-af61-406c6b7dff39","organization":"Qwen","rank_in_source_response":330,"raw_value":"0.0630213160333642","reported_by":"third_party","reported_date":"2025-10-03","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0630213160333642,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"39b64e04-7a69-4aa2-9e2e-fe38c24681ec","model_name":"Olmo 3.1 32B Think","obs_id":"artificial_analysis:humanitys-last-exam:39b64e04-7a69-4aa2-9e2e-fe38c24681ec","organization":"Allen Institute for AI","rank_in_source_response":332,"raw_value":"0.0625579240037071","reported_by":"third_party","reported_date":"2025-12-12","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0625579240037071,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"91f3a4c8-b000-4513-942c-bfe283375c35","model_name":"Ling 2.6 Flash","obs_id":"artificial_analysis:humanitys-last-exam:91f3a4c8-b000-4513-942c-bfe283375c35","organization":"InclusionAI","rank_in_source_response":332,"raw_value":"0.0625579240037071","reported_by":"third_party","reported_date":"2026-04-21","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0625579240037071,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"5a088cde-18e2-4dfa-98dd-d283e1c19654","model_name":"LFM2.5-1.2B-Thinking","obs_id":"artificial_analysis:humanitys-last-exam:5a088cde-18e2-4dfa-98dd-d283e1c19654","organization":"Liquid AI","rank_in_source_response":334,"raw_value":"0.06209453197405","reported_by":"third_party","reported_date":"2026-01-20","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.06209453197405,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"882a5da3-94ca-4602-8693-c45970df17e2","model_name":"Ling-flash-2.0","obs_id":"artificial_analysis:humanitys-last-exam:882a5da3-94ca-4602-8693-c45970df17e2","organization":"InclusionAI","rank_in_source_response":334,"raw_value":"0.06209453197405","reported_by":"third_party","reported_date":"2025-09-17","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.06209453197405,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"e1bfc488-5f48-4d42-abf6-7f3c53d79f9c","model_name":"LFM2.5-2.6B","obs_id":"artificial_analysis:humanitys-last-exam:e1bfc488-5f48-4d42-abf6-7f3c53d79f9c","organization":"Liquid AI","rank_in_source_response":334,"raw_value":"0.06209453197405","reported_by":"third_party","reported_date":"2026-08-04","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.06209453197405,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"c6a47d8a-7517-46e2-8383-329fe7241725","model_name":"Gemini 2.0 Pro Experimental (Feb '25)","obs_id":"artificial_analysis:humanitys-last-exam:c6a47d8a-7517-46e2-8383-329fe7241725","organization":"Google","rank_in_source_response":337,"raw_value":"0.0619","reported_by":"third_party","reported_date":"2025-02-05","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0619,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"2aacdc07-5f4e-4ab9-8ea5-5f7ab93f9eeb","model_name":"Qwen3 4B 2507 (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:2aacdc07-5f4e-4ab9-8ea5-5f7ab93f9eeb","organization":"Qwen","rank_in_source_response":338,"raw_value":"0.061631139944393","reported_by":"third_party","reported_date":"2025-08-06","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.061631139944393,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"504412c2-2ada-499b-aebf-7e0a35c9d286","model_name":"Claude 4 Opus (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:504412c2-2ada-499b-aebf-7e0a35c9d286","organization":"Anthropic","rank_in_source_response":338,"raw_value":"0.061631139944393","reported_by":"third_party","reported_date":"2025-05-22","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.061631139944393,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"3e6cf518-a1f4-42d3-8fcf-827c9bd8e6d5","model_name":"Qwen3 30B A3B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:3e6cf518-a1f4-42d3-8fcf-827c9bd8e6d5","organization":"Qwen","rank_in_source_response":340,"raw_value":"0.0616","reported_by":"third_party","reported_date":"2025-04-28","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0616,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"8e78cf7a-5b76-4beb-beba-b99c6233b208","model_name":"Solar Pro 2 (Preview) (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:8e78cf7a-5b76-4beb-beba-b99c6233b208","organization":"Upstage","rank_in_source_response":341,"raw_value":"0.0607043558850788","reported_by":"third_party","reported_date":"2025-05-20","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0607043558850788,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"c3738fb0-3408-4430-a699-760ae4b70c93","model_name":"GPT-5 (minimal)","obs_id":"artificial_analysis:humanitys-last-exam:c3738fb0-3408-4430-a699-760ae4b70c93","organization":"OpenAI","rank_in_source_response":342,"raw_value":"0.0602409638554217","reported_by":"third_party","reported_date":"2025-08-07","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0602409638554217,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"338216fb-62c2-48f1-898a-9166d12fb35e","model_name":"Olmo 3 7B Think","obs_id":"artificial_analysis:humanitys-last-exam:338216fb-62c2-48f1-898a-9166d12fb35e","organization":"Allen Institute for AI","rank_in_source_response":343,"raw_value":"0.0597775718257646","reported_by":"third_party","reported_date":"2025-11-20","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0597775718257646,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"d734e2ce-5cf8-467f-8148-586d02671333","model_name":"Exaone 4.0 1.2B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:d734e2ce-5cf8-467f-8148-586d02671333","organization":"LG AI Research","rank_in_source_response":343,"raw_value":"0.0597775718257646","reported_by":"third_party","reported_date":"2025-07-15","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0597775718257646,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"5d891609-fe1c-4e8d-b9f0-5b0ff6d9f439","model_name":"Tri-21B-Think","obs_id":"artificial_analysis:humanitys-last-exam:5d891609-fe1c-4e8d-b9f0-5b0ff6d9f439","organization":"Trillion Labs","rank_in_source_response":345,"raw_value":"0.0593141797961075","reported_by":"third_party","reported_date":"2026-02-10","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0593141797961075,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"6000145b-0e3d-4fef-a55f-bcaac84803b2","model_name":"DeepSeek R1 0528 Qwen3 8B","obs_id":"artificial_analysis:humanitys-last-exam:6000145b-0e3d-4fef-a55f-bcaac84803b2","organization":"DeepSeek","rank_in_source_response":345,"raw_value":"0.0593141797961075","reported_by":"third_party","reported_date":"2025-05-29","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0593141797961075,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"ae447455-940d-4d30-9139-a664fa896eaf","model_name":"GPT-5.4 mini (Non-Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:ae447455-940d-4d30-9139-a664fa896eaf","organization":"OpenAI","rank_in_source_response":347,"raw_value":"0.0588507877664504","reported_by":"third_party","reported_date":"2026-03-17","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0588507877664504,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"c99f3bde-7c08-4de8-bd5c-8ee9123ebffa","model_name":"gpt-oss-120b (low)","obs_id":"artificial_analysis:humanitys-last-exam:c99f3bde-7c08-4de8-bd5c-8ee9123ebffa","organization":"OpenAI","rank_in_source_response":347,"raw_value":"0.0588507877664504","reported_by":"third_party","reported_date":"2025-08-05","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0588507877664504,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"6056731b-c705-455b-aa0d-43cbf29b1054","model_name":"LongCat Flash Lite","obs_id":"artificial_analysis:humanitys-last-exam:6056731b-c705-455b-aa0d-43cbf29b1054","organization":"LongCat","rank_in_source_response":349,"raw_value":"0.0583873957367933","reported_by":"third_party","reported_date":"2026-01-28","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0583873957367933,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"60cff809-05fb-4439-afe7-8b1476439f49","model_name":"Tri-21B-think Preview","obs_id":"artificial_analysis:humanitys-last-exam:60cff809-05fb-4439-afe7-8b1476439f49","organization":"Trillion Labs","rank_in_source_response":350,"raw_value":"0.0579240037071362","reported_by":"third_party","reported_date":"2026-02-10","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0579240037071362,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"8f74a6ed-f82f-4a2f-a96b-4914993e47da","model_name":"Olmo 3 7B Instruct","obs_id":"artificial_analysis:humanitys-last-exam:8f74a6ed-f82f-4a2f-a96b-4914993e47da","organization":"Allen Institute for AI","rank_in_source_response":350,"raw_value":"0.0579240037071362","reported_by":"third_party","reported_date":"2025-11-20","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0579240037071362,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"8273650d-40e5-45ee-aeda-df71de784164","model_name":"Exaone 4.0 1.2B (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:8273650d-40e5-45ee-aeda-df71de784164","organization":"LG AI Research","rank_in_source_response":352,"raw_value":"0.0569972196478221","reported_by":"third_party","reported_date":"2025-07-15","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0569972196478221,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"9cc377dc-67ae-4042-bafc-0466b5f05089","model_name":"K-EXAONE (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:9cc377dc-67ae-4042-bafc-0466b5f05089","organization":"LG AI Research","rank_in_source_response":352,"raw_value":"0.0569972196478221","reported_by":"third_party","reported_date":"2025-12-31","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0569972196478221,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"4ae6c88d-9e4a-4850-89fe-18a1c04a66cc","model_name":"Qwen3 0.6B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:4ae6c88d-9e4a-4850-89fe-18a1c04a66cc","organization":"Qwen","rank_in_source_response":354,"raw_value":"0.0564","reported_by":"third_party","reported_date":"2025-04-28","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0564,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"1a8ba535-df18-459b-ad40-3199191296d7","model_name":"Llama 3.3 Nemotron Super 49B v1 (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:1a8ba535-df18-459b-ad40-3199191296d7","organization":"NVIDIA","rank_in_source_response":355,"raw_value":"0.0562","reported_by":"third_party","reported_date":"2025-03-18","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0562,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"0faadeeb-320c-45cf-9c76-5f8768f342e6","model_name":"LFM2 1.2B","obs_id":"artificial_analysis:humanitys-last-exam:0faadeeb-320c-45cf-9c76-5f8768f342e6","organization":"Liquid AI","rank_in_source_response":356,"raw_value":"0.0556070435588508","reported_by":"third_party","reported_date":"2025-07-10","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0556070435588508,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"5fb47ff6-a30e-4c2c-96f2-55e95a13390f","model_name":"Llama 3.2 Instruct 11B (Vision)","obs_id":"artificial_analysis:humanitys-last-exam:5fb47ff6-a30e-4c2c-96f2-55e95a13390f","organization":"Meta","rank_in_source_response":357,"raw_value":"0.0553","reported_by":"third_party","reported_date":"2024-09-25","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0553,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"54c7f3fc-7078-442a-b472-e8691257a88c","model_name":"Granite 4.0 350M","obs_id":"artificial_analysis:humanitys-last-exam:54c7f3fc-7078-442a-b472-e8691257a88c","organization":"IBM","rank_in_source_response":358,"raw_value":"0.0551436515291937","reported_by":"third_party","reported_date":"2025-10-28","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0551436515291937,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"6e6e02fd-9cbd-417f-9bfc-673df89c313d","model_name":"NVIDIA Nemotron Nano 12B v2 VL (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:6e6e02fd-9cbd-417f-9bfc-673df89c313d","organization":"NVIDIA","rank_in_source_response":358,"raw_value":"0.0551436515291937","reported_by":"third_party","reported_date":"2025-10-28","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0551436515291937,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"339a92c1-8a42-417f-8d1f-cdbc605acd9e","model_name":"HyperCLOVA X SEED Think (32B)","obs_id":"artificial_analysis:humanitys-last-exam:339a92c1-8a42-417f-8d1f-cdbc605acd9e","organization":"Naver","rank_in_source_response":360,"raw_value":"0.0546802594995366","reported_by":"third_party","reported_date":"2025-12-26","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0546802594995366,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"49e70a38-4ac1-4659-b490-09b2c7ff21d6","model_name":"Apertus 70B Instruct","obs_id":"artificial_analysis:humanitys-last-exam:49e70a38-4ac1-4659-b490-09b2c7ff21d6","organization":"Swiss AI Initiative","rank_in_source_response":360,"raw_value":"0.0546802594995366","reported_by":"third_party","reported_date":"2025-09-02","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0546802594995366,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"739e531a-eb0a-478f-bb67-5845b79ce65d","model_name":"LFM2 2.6B","obs_id":"artificial_analysis:humanitys-last-exam:739e531a-eb0a-478f-bb67-5845b79ce65d","organization":"Liquid AI","rank_in_source_response":360,"raw_value":"0.0546802594995366","reported_by":"third_party","reported_date":"2025-09-23","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0546802594995366,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"946e7aab-db1c-4c3f-b0b3-7720d0cff187","model_name":"GLM-4.6 (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:946e7aab-db1c-4c3f-b0b3-7720d0cff187","organization":"Z.ai","rank_in_source_response":360,"raw_value":"0.0546802594995366","reported_by":"third_party","reported_date":"2025-09-30","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0546802594995366,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"80f7860a-7665-4658-9f05-15bccf5f832f","model_name":"Llama 3.2 Instruct 1B","obs_id":"artificial_analysis:humanitys-last-exam:80f7860a-7665-4658-9f05-15bccf5f832f","organization":"Meta","rank_in_source_response":364,"raw_value":"0.0546","reported_by":"third_party","reported_date":"2024-09-25","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0546,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"66f4ce73-9a9b-4b49-9c6e-bedb9bfdc720","model_name":"Ministral 3 3B","obs_id":"artificial_analysis:humanitys-last-exam:66f4ce73-9a9b-4b49-9c6e-bedb9bfdc720","organization":"Mistral","rank_in_source_response":365,"raw_value":"0.0537534754402224","reported_by":"third_party","reported_date":"2025-12-02","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0537534754402224,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"f818a7bb-6f23-4b24-8d52-6b9c1a5ca628","model_name":"OLMo 2 7B","obs_id":"artificial_analysis:humanitys-last-exam:f818a7bb-6f23-4b24-8d52-6b9c1a5ca628","organization":"Allen Institute for AI","rank_in_source_response":365,"raw_value":"0.0537534754402224","reported_by":"third_party","reported_date":"2024-11-26","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0537534754402224,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"c7327e6e-b27f-4b1b-859d-159a34e0ba1c","model_name":"DeepSeek Coder V2 Lite Instruct","obs_id":"artificial_analysis:humanitys-last-exam:c7327e6e-b27f-4b1b-859d-159a34e0ba1c","organization":"DeepSeek","rank_in_source_response":367,"raw_value":"0.0536","reported_by":"third_party","reported_date":"2024-06-17","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0536,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"71e8d48c-1920-4f27-8ea9-1f10becc615a","model_name":"Llama 3.2 Instruct 3B","obs_id":"artificial_analysis:humanitys-last-exam:71e8d48c-1920-4f27-8ea9-1f10becc615a","organization":"Meta","rank_in_source_response":368,"raw_value":"0.0535","reported_by":"third_party","reported_date":"2024-09-25","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0535,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"ffd65ef7-fbdb-4145-98ae-b5d01cda770b","model_name":"Llama 2 Chat 7B","obs_id":"artificial_analysis:humanitys-last-exam:ffd65ef7-fbdb-4145-98ae-b5d01cda770b","organization":"Meta","rank_in_source_response":369,"raw_value":"0.0533","reported_by":"third_party","reported_date":"2023-07-18","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0533,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"d1720545-d0a8-4c15-a53e-ef5ca99ac7ea","model_name":"Gemma 3 1B Instruct","obs_id":"artificial_analysis:humanitys-last-exam:d1720545-d0a8-4c15-a53e-ef5ca99ac7ea","organization":"Google","rank_in_source_response":370,"raw_value":"0.0532900834105653","reported_by":"third_party","reported_date":"2025-03-13","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0532900834105653,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"2bb84433-f38e-4edc-9b65-4d7b1f473db9","model_name":"Qwen3 1.7B (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:2bb84433-f38e-4edc-9b65-4d7b1f473db9","organization":"Qwen","rank_in_source_response":371,"raw_value":"0.0532","reported_by":"third_party","reported_date":"2025-04-28","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0532,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"222fb320-6e55-4672-846a-b6d5a24a45f4","model_name":"Gemma 3 4B Instruct","obs_id":"artificial_analysis:humanitys-last-exam:222fb320-6e55-4672-846a-b6d5a24a45f4","organization":"Google","rank_in_source_response":372,"raw_value":"0.0529","reported_by":"third_party","reported_date":"2025-03-12","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0529,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"739684ba-0f63-4e2a-b4ee-30741c9e9320","model_name":"Llama 3.1 Instruct 8B","obs_id":"artificial_analysis:humanitys-last-exam:739684ba-0f63-4e2a-b4ee-30741c9e9320","organization":"Meta","rank_in_source_response":372,"raw_value":"0.0529","reported_by":"third_party","reported_date":"2024-07-23","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0529,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"16149b9c-a1e9-4669-a5cb-ff3c00d78f89","model_name":"gpt-oss-20b (low)","obs_id":"artificial_analysis:humanitys-last-exam:16149b9c-a1e9-4669-a5cb-ff3c00d78f89","organization":"OpenAI","rank_in_source_response":374,"raw_value":"0.0528266913809083","reported_by":"third_party","reported_date":"2025-08-05","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0528266913809083,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"d0b3d47e-aec6-425e-9de7-168dcc6d1e28","model_name":"GPT-5.1 (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:d0b3d47e-aec6-425e-9de7-168dcc6d1e28","organization":"OpenAI","rank_in_source_response":374,"raw_value":"0.0528266913809083","reported_by":"third_party","reported_date":"2025-11-13","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0528266913809083,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"81444bc8-72f9-4a2d-ad43-27e3f0d2f461","model_name":"Tiny Aya Global","obs_id":"artificial_analysis:humanitys-last-exam:81444bc8-72f9-4a2d-ad43-27e3f0d2f461","organization":"Cohere","rank_in_source_response":376,"raw_value":"0.0523632993512512","reported_by":"third_party","reported_date":"2026-02-17","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0523632993512512,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"599da8e0-bd9c-4b38-a127-b50e371fbcf8","model_name":"Llama 2 Chat 70B","obs_id":"artificial_analysis:humanitys-last-exam:599da8e0-bd9c-4b38-a127-b50e371fbcf8","organization":"Meta","rank_in_source_response":377,"raw_value":"0.0521","reported_by":"third_party","reported_date":"2023-07-18","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0521,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"b1fa84f8-1ed3-4124-b403-4655dafa4267","model_name":"Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:b1fa84f8-1ed3-4124-b403-4655dafa4267","organization":"NVIDIA","rank_in_source_response":378,"raw_value":"0.0518999073215941","reported_by":"third_party","reported_date":"2025-05-20","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0518999073215941,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"f4274721-ef28-4121-aa88-8e97267a5a82","model_name":"Nova 2.0 Pro Preview (low)","obs_id":"artificial_analysis:humanitys-last-exam:f4274721-ef28-4121-aa88-8e97267a5a82","organization":"Amazon","rank_in_source_response":378,"raw_value":"0.0518999073215941","reported_by":"third_party","reported_date":"2025-11-27","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0518999073215941,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"af74f222-05c7-422d-a653-b9c0707c9c72","model_name":"Molmo 7B-D","obs_id":"artificial_analysis:humanitys-last-exam:af74f222-05c7-422d-a653-b9c0707c9c72","organization":"Allen Institute for AI","rank_in_source_response":380,"raw_value":"0.051436515291937","reported_by":"third_party","reported_date":"2024-09-25","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.051436515291937,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"540ebc58-a2d8-4dc9-ba6b-973efa52fab1","model_name":"Jamba 1.5 Mini","obs_id":"artificial_analysis:humanitys-last-exam:540ebc58-a2d8-4dc9-ba6b-973efa52fab1","organization":"AI21 Labs","rank_in_source_response":381,"raw_value":"0.0514","reported_by":"third_party","reported_date":"2024-08-22","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0514,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"4a845d7b-a52d-43bb-80b7-b58c7a0c155e","model_name":"DeepSeek R1 Distill Llama 70B","obs_id":"artificial_analysis:humanitys-last-exam:4a845d7b-a52d-43bb-80b7-b58c7a0c155e","organization":"DeepSeek","rank_in_source_response":382,"raw_value":"0.0513","reported_by":"third_party","reported_date":"2025-01-20","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0513,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"3c5289e5-1c62-434c-bc44-c51c39f640a1","model_name":"LFM2.5-VL-1.6B","obs_id":"artificial_analysis:humanitys-last-exam:3c5289e5-1c62-434c-bc44-c51c39f640a1","organization":"Liquid AI","rank_in_source_response":383,"raw_value":"0.0509731232622799","reported_by":"third_party","reported_date":"2026-01-05","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0509731232622799,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"405e2235-0925-4634-a3c7-fbd5f6394bc0","model_name":"Qwen3.5 0.8B (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:405e2235-0925-4634-a3c7-fbd5f6394bc0","organization":"Qwen","rank_in_source_response":383,"raw_value":"0.0509731232622799","reported_by":"third_party","reported_date":"2026-03-02","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0509731232622799,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"49fd01f9-887d-4479-b8ce-771a81ecef4e","model_name":"Grok 4.1 Fast (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:49fd01f9-887d-4479-b8ce-771a81ecef4e","organization":"xAI","rank_in_source_response":383,"raw_value":"0.0509731232622799","reported_by":"third_party","reported_date":"2025-11-19","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0509731232622799,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"71f51ea9-94fe-4635-a80d-4cfffbb685f4","model_name":"Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:71f51ea9-94fe-4635-a80d-4cfffbb685f4","organization":"Google","rank_in_source_response":383,"raw_value":"0.0509731232622799","reported_by":"third_party","reported_date":"2025-09-25","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0509731232622799,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"82879bb8-89fb-4adc-b519-315b8ef30b77","model_name":"Llama 3 Instruct 8B","obs_id":"artificial_analysis:humanitys-last-exam:82879bb8-89fb-4adc-b519-315b8ef30b77","organization":"Meta","rank_in_source_response":387,"raw_value":"0.0506","reported_by":"third_party","reported_date":"2024-04-18","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0506,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"3d64bf83-232e-427e-8590-26b478bae4a8","model_name":"Ling-mini-2.0","obs_id":"artificial_analysis:humanitys-last-exam:3d64bf83-232e-427e-8590-26b478bae4a8","organization":"InclusionAI","rank_in_source_response":388,"raw_value":"0.0505097312326228","reported_by":"third_party","reported_date":"2025-09-09","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0505097312326228,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"433e410e-5170-4f03-b92f-7927c220b2fe","model_name":"MiniCPM-V 4.6 1.3B","obs_id":"artificial_analysis:humanitys-last-exam:433e410e-5170-4f03-b92f-7927c220b2fe","organization":"OpenBMB","rank_in_source_response":388,"raw_value":"0.0505097312326228","reported_by":"third_party","reported_date":"2026-05-11","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0505097312326228,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"bc26bfdb-4923-4442-a6ca-e77392923581","model_name":"GPT-5 mini (minimal)","obs_id":"artificial_analysis:humanitys-last-exam:bc26bfdb-4923-4442-a6ca-e77392923581","organization":"OpenAI","rank_in_source_response":388,"raw_value":"0.0505097312326228","reported_by":"third_party","reported_date":"2025-08-07","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0505097312326228,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"9f7c7566-a704-49a2-a383-cb3181da33a4","model_name":"GPT-4.1 mini","obs_id":"artificial_analysis:humanitys-last-exam:9f7c7566-a704-49a2-a383-cb3181da33a4","organization":"OpenAI","rank_in_source_response":391,"raw_value":"0.0502","reported_by":"third_party","reported_date":"2025-04-14","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0502,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"1fc32894-1060-493b-af94-62bb1068555e","model_name":"Granite 4.0 Micro","obs_id":"artificial_analysis:humanitys-last-exam:1fc32894-1060-493b-af94-62bb1068555e","organization":"IBM","rank_in_source_response":392,"raw_value":"0.0500463392029657","reported_by":"third_party","reported_date":"2025-09-22","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0500463392029657,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"2f60d80d-c3d3-4a43-bded-0557898c4618","model_name":"EXAONE 4.0 32B (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:2f60d80d-c3d3-4a43-bded-0557898c4618","organization":"LG AI Research","rank_in_source_response":392,"raw_value":"0.0500463392029657","reported_by":"third_party","reported_date":"2025-07-15","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0500463392029657,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"94a6d26e-a903-47f3-8323-ae422d237bb9","model_name":"Olmo 3.1 32B Instruct","obs_id":"artificial_analysis:humanitys-last-exam:94a6d26e-a903-47f3-8323-ae422d237bb9","organization":"Allen Institute for AI","rank_in_source_response":392,"raw_value":"0.0500463392029657","reported_by":"third_party","reported_date":"2026-01-13","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0500463392029657,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"dafbb6d2-4825-43d1-a927-feedcfd2e998","model_name":"Granite 4.0 H 1B","obs_id":"artificial_analysis:humanitys-last-exam:dafbb6d2-4825-43d1-a927-feedcfd2e998","organization":"IBM","rank_in_source_response":392,"raw_value":"0.0500463392029657","reported_by":"third_party","reported_date":"2025-10-28","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0500463392029657,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"2cd04201-2b6e-47ef-853e-7601f705f2a8","model_name":"Phi-4 Multimodal Instruct","obs_id":"artificial_analysis:humanitys-last-exam:2cd04201-2b6e-47ef-853e-7601f705f2a8","organization":"Microsoft","rank_in_source_response":396,"raw_value":"0.05","reported_by":"third_party","reported_date":"2025-02-26","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.05,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"ded8d96e-835f-4359-947a-a4c3bb78e983","model_name":"Phi-3 Mini Instruct 3.8B","obs_id":"artificial_analysis:humanitys-last-exam:ded8d96e-835f-4359-947a-a4c3bb78e983","organization":"Microsoft","rank_in_source_response":397,"raw_value":"0.0496","reported_by":"third_party","reported_date":"2024-04-23","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0496,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"0985ada8-2ed8-404d-bd8b-7357666ce40f","model_name":"Qwen3.5 2B (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:0985ada8-2ed8-404d-bd8b-7357666ce40f","organization":"Qwen","rank_in_source_response":398,"raw_value":"0.0495829471733086","reported_by":"third_party","reported_date":"2026-03-02","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0495829471733086,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"891bcdf2-8dd2-4dc3-829b-d963fde25876","model_name":"Apertus 8B Instruct","obs_id":"artificial_analysis:humanitys-last-exam:891bcdf2-8dd2-4dc3-829b-d963fde25876","organization":"Swiss AI Initiative","rank_in_source_response":398,"raw_value":"0.0495829471733086","reported_by":"third_party","reported_date":"2025-09-02","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0495829471733086,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"c8673741-5e1a-46a1-9e4f-710a5c920982","model_name":"GLM-4.7-Flash (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:c8673741-5e1a-46a1-9e4f-710a5c920982","organization":"Z.ai","rank_in_source_response":398,"raw_value":"0.0495829471733086","reported_by":"third_party","reported_date":"2026-01-19","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0495829471733086,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"0e5f6140-1154-4583-a3e0-8c032a338892","model_name":"Qwen3 0.6B (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:0e5f6140-1154-4583-a3e0-8c032a338892","organization":"Qwen","rank_in_source_response":401,"raw_value":"0.0493","reported_by":"third_party","reported_date":"2025-04-28","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0493,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"1299b9a8-af50-4742-a58b-24ff7eb48f9f","model_name":"LFM 40B","obs_id":"artificial_analysis:humanitys-last-exam:1299b9a8-af50-4742-a58b-24ff7eb48f9f","organization":"Liquid AI","rank_in_source_response":401,"raw_value":"0.0493","reported_by":"third_party","reported_date":"2024-09-30","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0493,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"686ab020-ee58-4a70-a9ac-24d675a73506","model_name":"LFM2 8B A1B","obs_id":"artificial_analysis:humanitys-last-exam:686ab020-ee58-4a70-a9ac-24d675a73506","organization":"Liquid AI","rank_in_source_response":403,"raw_value":"0.0491195551436515","reported_by":"third_party","reported_date":"2025-10-07","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0491195551436515,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"922c69c7-9037-43c6-8bcf-a1c555e7f3eb","model_name":"Llama 4 Maverick","obs_id":"artificial_analysis:humanitys-last-exam:922c69c7-9037-43c6-8bcf-a1c555e7f3eb","organization":"Meta","rank_in_source_response":403,"raw_value":"0.0491195551436515","reported_by":"third_party","reported_date":"2025-04-05","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0491195551436515,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"e410e854-104d-4b35-a171-899ff9d974bb","model_name":"Qwen2.5 Coder Instruct 7B","obs_id":"artificial_analysis:humanitys-last-exam:e410e854-104d-4b35-a171-899ff9d974bb","organization":"Qwen","rank_in_source_response":405,"raw_value":"0.0489","reported_by":"third_party","reported_date":"2024-09-19","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0489,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"5ec4a0db-da66-4e46-9682-fceeed755ef8","model_name":"Sonar","obs_id":"artificial_analysis:humanitys-last-exam:5ec4a0db-da66-4e46-9682-fceeed755ef8","organization":"Perplexity","rank_in_source_response":406,"raw_value":"0.0488","reported_by":"third_party","reported_date":"2025-01-21","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0488,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"9ee13921-62a4-425a-a22b-df3302198d93","model_name":"NVIDIA Nemotron 3 Nano 4B","obs_id":"artificial_analysis:humanitys-last-exam:9ee13921-62a4-425a-a22b-df3302198d93","organization":"NVIDIA","rank_in_source_response":407,"raw_value":"0.0486561631139944","reported_by":"third_party","reported_date":"2026-03-16","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0486561631139944,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"f1d52583-9d20-4099-99ac-b5df9430c3b6","model_name":"NVIDIA Nemotron Nano 9B V2 (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:f1d52583-9d20-4099-99ac-b5df9430c3b6","organization":"NVIDIA","rank_in_source_response":407,"raw_value":"0.0486561631139944","reported_by":"third_party","reported_date":"2025-08-18","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0486561631139944,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"5303601c-8133-4f52-bc4e-5241ee6b3c10","model_name":"Gemma 4 E4B (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:5303601c-8133-4f52-bc4e-5241ee6b3c10","organization":"Google","rank_in_source_response":409,"raw_value":"0.0481927710843374","reported_by":"third_party","reported_date":"2026-04-03","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0481927710843374,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"8c748e53-61ae-48b8-af8d-eb8298b1e9db","model_name":"Nemotron 3 Nano Omni 30B A3B Reasoning","obs_id":"artificial_analysis:humanitys-last-exam:8c748e53-61ae-48b8-af8d-eb8298b1e9db","organization":"NVIDIA","rank_in_source_response":409,"raw_value":"0.0481927710843374","reported_by":"third_party","reported_date":"2026-04-29","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0481927710843374,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"a2c8e7b2-57bf-4d1e-96ea-7944d786d94d","model_name":"Granite 4.0 1B","obs_id":"artificial_analysis:humanitys-last-exam:a2c8e7b2-57bf-4d1e-96ea-7944d786d94d","organization":"IBM","rank_in_source_response":409,"raw_value":"0.0481927710843374","reported_by":"third_party","reported_date":"2025-10-28","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0481927710843374,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"bd2c3517-00d8-4ba5-a989-1f1e52f3ffab","model_name":"Gemma 3n E4B Instruct Preview (May '25)","obs_id":"artificial_analysis:humanitys-last-exam:bd2c3517-00d8-4ba5-a989-1f1e52f3ffab","organization":"Google","rank_in_source_response":409,"raw_value":"0.0481927710843374","reported_by":"third_party","reported_date":"2025-05-20","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0481927710843374,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"abe9f0c7-f4f6-430d-ba42-f45afdd4841b","model_name":"Command-R (Mar '24)","obs_id":"artificial_analysis:humanitys-last-exam:abe9f0c7-f4f6-430d-ba42-f45afdd4841b","organization":"Cohere","rank_in_source_response":413,"raw_value":"0.0479","reported_by":"third_party","reported_date":"2024-03-12","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0479,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"ec60e57e-76d3-42e3-a0e3-80662225a639","model_name":"OpenChat 3.5 (1210)","obs_id":"artificial_analysis:humanitys-last-exam:ec60e57e-76d3-42e3-a0e3-80662225a639","organization":"OpenChat","rank_in_source_response":413,"raw_value":"0.0479","reported_by":"third_party","reported_date":"2023-12-18","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0479,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"b07aef0a-b192-46a1-b1c9-40b06d1b9061","model_name":"Gemma 4 E2B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:b07aef0a-b192-46a1-b1c9-40b06d1b9061","organization":"Google","rank_in_source_response":415,"raw_value":"0.0477293790546803","reported_by":"third_party","reported_date":"2026-04-02","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0477293790546803,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"6b08a75a-19ee-40b4-be33-133b8ef42f92","model_name":"Llama 2 Chat 13B","obs_id":"artificial_analysis:humanitys-last-exam:6b08a75a-19ee-40b4-be33-133b8ef42f92","organization":"Meta","rank_in_source_response":416,"raw_value":"0.0477","reported_by":"third_party","reported_date":"2023-07-18","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0477,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"75e1c197-f239-4361-a9d6-66dccfead236","model_name":"DeepSeek V3 0324","obs_id":"artificial_analysis:humanitys-last-exam:75e1c197-f239-4361-a9d6-66dccfead236","organization":"DeepSeek","rank_in_source_response":417,"raw_value":"0.0474","reported_by":"third_party","reported_date":"2025-03-25","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0474,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"6afbfb62-27e4-435e-9c85-d9fe1b92519e","model_name":"Gemini 2.5 Flash (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:6afbfb62-27e4-435e-9c85-d9fe1b92519e","organization":"Google","rank_in_source_response":418,"raw_value":"0.0472659870250232","reported_by":"third_party","reported_date":"2025-05-20","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0472659870250232,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"755d7281-2ed8-48c7-808f-709ec4cbfb71","model_name":"Gemma 4 E2B (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:755d7281-2ed8-48c7-808f-709ec4cbfb71","organization":"Google","rank_in_source_response":418,"raw_value":"0.0472659870250232","reported_by":"third_party","reported_date":"2026-04-02","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0472659870250232,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"94229066-9381-4ee1-bf70-a16d63756a6e","model_name":"Gemini 1.5 Flash-8B","obs_id":"artificial_analysis:humanitys-last-exam:94229066-9381-4ee1-bf70-a16d63756a6e","organization":"Google","rank_in_source_response":420,"raw_value":"0.0469","reported_by":"third_party","reported_date":"2024-10-03","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0469,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"05a32e26-e609-4377-951b-8fa23d329926","model_name":"Mistral Medium 3.1","obs_id":"artificial_analysis:humanitys-last-exam:05a32e26-e609-4377-951b-8fa23d329926","organization":"Mistral","rank_in_source_response":421,"raw_value":"0.0468025949953661","reported_by":"third_party","reported_date":"2025-08-12","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0468025949953661,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"3edcb2ed-6981-4f88-a556-563f7f8f00aa","model_name":"Mixtral 8x7B Instruct","obs_id":"artificial_analysis:humanitys-last-exam:3edcb2ed-6981-4f88-a556-563f7f8f00aa","organization":"Mistral","rank_in_source_response":422,"raw_value":"0.0468","reported_by":"third_party","reported_date":"2023-12-11","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0468,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"2ac96b67-f4f8-4c8c-ac08-c7510faa7bb9","model_name":"Gemini 1.5 Pro (Sep '24)","obs_id":"artificial_analysis:humanitys-last-exam:2ac96b67-f4f8-4c8c-ac08-c7510faa7bb9","organization":"Google","rank_in_source_response":423,"raw_value":"0.0464","reported_by":"third_party","reported_date":"2024-09-24","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0464,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"5962d643-0a6f-4630-bb08-ab5720d80056","model_name":"Qwen3 1.7B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:5962d643-0a6f-4630-bb08-ab5720d80056","organization":"Qwen","rank_in_source_response":423,"raw_value":"0.0464","reported_by":"third_party","reported_date":"2025-04-28","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0464,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"0b226b82-1462-4860-bf1a-f8aed7024791","model_name":"Qwen3 Omni 30B A3B Instruct","obs_id":"artificial_analysis:humanitys-last-exam:0b226b82-1462-4860-bf1a-f8aed7024791","organization":"Qwen","rank_in_source_response":425,"raw_value":"0.046339202965709","reported_by":"third_party","reported_date":"2025-09-22","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.046339202965709,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"344c6718-c573-41d4-9556-10287a3fa1fc","model_name":"Nova Micro","obs_id":"artificial_analysis:humanitys-last-exam:344c6718-c573-41d4-9556-10287a3fa1fc","organization":"Amazon","rank_in_source_response":425,"raw_value":"0.046339202965709","reported_by":"third_party","reported_date":"2024-12-03","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.046339202965709,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"713fae11-c75c-4f10-ae2c-8e4074cd58af","model_name":"Ministral 3 14B","obs_id":"artificial_analysis:humanitys-last-exam:713fae11-c75c-4f10-ae2c-8e4074cd58af","organization":"Mistral","rank_in_source_response":425,"raw_value":"0.046339202965709","reported_by":"third_party","reported_date":"2025-12-02","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.046339202965709,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"76361085-f5dc-49ec-b069-fe56ca885933","model_name":"Command-R+ (Apr '24)","obs_id":"artificial_analysis:humanitys-last-exam:76361085-f5dc-49ec-b069-fe56ca885933","organization":"Cohere","rank_in_source_response":428,"raw_value":"0.0463","reported_by":"third_party","reported_date":"2024-04-04","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0463,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"f3169f25-8c6f-48e4-ae87-0cf872dc0ec1","model_name":"Qwen3 30B A3B (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:f3169f25-8c6f-48e4-ae87-0cf872dc0ec1","organization":"Qwen","rank_in_source_response":429,"raw_value":"0.046","reported_by":"third_party","reported_date":"2025-04-28","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.046,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"23b379f7-18df-492a-9fc1-a56c5a5b9cfc","model_name":"NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:23b379f7-18df-492a-9fc1-a56c5a5b9cfc","organization":"NVIDIA","rank_in_source_response":430,"raw_value":"0.0458758109360519","reported_by":"third_party","reported_date":"2025-12-15","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0458758109360519,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"2e8694f9-7782-47a6-a6ba-fdce89d939c8","model_name":"NVIDIA Nemotron Nano 9B V2 (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:2e8694f9-7782-47a6-a6ba-fdce89d939c8","organization":"NVIDIA","rank_in_source_response":430,"raw_value":"0.0458758109360519","reported_by":"third_party","reported_date":"2025-08-18","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0458758109360519,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"f93d0750-b659-4ceb-a123-7e657904ef2b","model_name":"Qwen3 VL 4B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:f93d0750-b659-4ceb-a123-7e657904ef2b","organization":"Qwen","rank_in_source_response":430,"raw_value":"0.0458758109360519","reported_by":"third_party","reported_date":"2025-10-14","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0458758109360519,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"df95f83f-5ebb-466a-9d2d-b95efc8c012c","model_name":"DeepSeek R1 Distill Qwen 32B","obs_id":"artificial_analysis:humanitys-last-exam:df95f83f-5ebb-466a-9d2d-b95efc8c012c","organization":"DeepSeek","rank_in_source_response":433,"raw_value":"0.0458","reported_by":"third_party","reported_date":"2025-01-20","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0458,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"217b34ec-5920-4fc1-8886-6a70a324837d","model_name":"Mistral 7B Instruct","obs_id":"artificial_analysis:humanitys-last-exam:217b34ec-5920-4fc1-8886-6a70a324837d","organization":"Mistral","rank_in_source_response":434,"raw_value":"0.0455","reported_by":"third_party","reported_date":"2023-09-27","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0455,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"093883ed-f5fc-443b-8e18-afbfb166699e","model_name":"Qwen3 Coder 480B A35B Instruct","obs_id":"artificial_analysis:humanitys-last-exam:093883ed-f5fc-443b-8e18-afbfb166699e","organization":"Qwen","rank_in_source_response":435,"raw_value":"0.0454124189063948","reported_by":"third_party","reported_date":"2025-07-22","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0454124189063948,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"2dbb6dc7-8c40-4b6d-af9c-cf805f83b79a","model_name":"Grok 4 Fast (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:2dbb6dc7-8c40-4b6d-af9c-cf805f83b79a","organization":"xAI","rank_in_source_response":435,"raw_value":"0.0454124189063948","reported_by":"third_party","reported_date":"2025-09-19","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0454124189063948,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"d306cccd-0085-4b2f-8aa0-ffcdbb434695","model_name":"MiniCPM5-1B (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:d306cccd-0085-4b2f-8aa0-ffcdbb434695","organization":"OpenBMB","rank_in_source_response":435,"raw_value":"0.0454124189063948","reported_by":"third_party","reported_date":"2026-05-25","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0454124189063948,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"4559e9f0-8aad-4681-89fb-68cb915e0f16","model_name":"Qwen3 14B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:4559e9f0-8aad-4681-89fb-68cb915e0f16","organization":"Qwen","rank_in_source_response":438,"raw_value":"0.0453","reported_by":"third_party","reported_date":"2025-04-28","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0453,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"aa83359a-d804-4f0b-b5bf-dc637711c26f","model_name":"Llama 3 Instruct 70B","obs_id":"artificial_analysis:humanitys-last-exam:aa83359a-d804-4f0b-b5bf-dc637711c26f","organization":"Meta","rank_in_source_response":439,"raw_value":"0.0452","reported_by":"third_party","reported_date":"2024-04-18","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0452,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"2ffa7571-fa78-453a-b589-9aa3fac702d2","model_name":"G9v3-3B","obs_id":"artificial_analysis:humanitys-last-exam:2ffa7571-fa78-453a-b589-9aa3fac702d2","organization":"AI9Stars","rank_in_source_response":440,"raw_value":"0.0449490268767377","reported_by":"third_party","reported_date":"2026-07-23","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0449490268767377,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"a797eaf3-6d75-4f29-86a8-e1243ce52d43","model_name":"Gemma 3n E4B Instruct","obs_id":"artificial_analysis:humanitys-last-exam:a797eaf3-6d75-4f29-86a8-e1243ce52d43","organization":"Google","rank_in_source_response":440,"raw_value":"0.0449490268767377","reported_by":"third_party","reported_date":"2025-06-26","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0449490268767377,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"b0249961-b8b2-479d-8325-a29ea17c7b89","model_name":"Qwen3 4B 2507 Instruct","obs_id":"artificial_analysis:humanitys-last-exam:b0249961-b8b2-479d-8325-a29ea17c7b89","organization":"Qwen","rank_in_source_response":440,"raw_value":"0.0449490268767377","reported_by":"third_party","reported_date":"2025-08-06","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0449490268767377,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"9ca71ac4-41c8-42c0-87dd-5704a9e5b94d","model_name":"Llama 3.2 Instruct 90B (Vision)","obs_id":"artificial_analysis:humanitys-last-exam:9ca71ac4-41c8-42c0-87dd-5704a9e5b94d","organization":"Meta","rank_in_source_response":443,"raw_value":"0.0449","reported_by":"third_party","reported_date":"2024-09-25","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0449,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"466aecdb-3d96-4191-bc52-b3366db38851","model_name":"Llama 3.1 Instruct 70B","obs_id":"artificial_analysis:humanitys-last-exam:466aecdb-3d96-4191-bc52-b3366db38851","organization":"Meta","rank_in_source_response":444,"raw_value":"0.0447","reported_by":"third_party","reported_date":"2024-07-23","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0447,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"9f873c2f-2c2d-4ccb-9e1b-71bf61b052be","model_name":"Phi-4 Mini Instruct","obs_id":"artificial_analysis:humanitys-last-exam:9f873c2f-2c2d-4ccb-9e1b-71bf61b052be","organization":"Microsoft","rank_in_source_response":445,"raw_value":"0.0445","reported_by":"third_party","reported_date":"2024-02-26","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0445,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"a04f5b78-f397-4fd8-a2b1-00dcab50324c","model_name":"Grok Beta","obs_id":"artificial_analysis:humanitys-last-exam:a04f5b78-f397-4fd8-a2b1-00dcab50324c","organization":"xAI","rank_in_source_response":445,"raw_value":"0.0445","reported_by":"third_party","reported_date":"2024-08-13","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0445,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"b4f14013-37dd-4c75-bd8a-378365d9ed77","model_name":"Jamba 1.7 Mini","obs_id":"artificial_analysis:humanitys-last-exam:b4f14013-37dd-4c75-bd8a-378365d9ed77","organization":"AI21 Labs","rank_in_source_response":447,"raw_value":"0.0444856348470806","reported_by":"third_party","reported_date":"2025-07-07","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0444856348470806,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"dbbcf240-a69e-4078-8f16-7c94c7a8c514","model_name":"Reka Flash 3","obs_id":"artificial_analysis:humanitys-last-exam:dbbcf240-a69e-4078-8f16-7c94c7a8c514","organization":"Reka AI","rank_in_source_response":448,"raw_value":"0.0444","reported_by":"third_party","reported_date":"2025-03-10","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0444,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"191a2097-cce3-49cf-881e-0c790892059f","model_name":"Qwen3 4B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:191a2097-cce3-49cf-881e-0c790892059f","organization":"Qwen","rank_in_source_response":449,"raw_value":"0.0442","reported_by":"third_party","reported_date":"2025-04-28","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0442,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"2bfdd17a-e027-4068-a54e-b0e90a6df118","model_name":"Gemma 3 27B Instruct","obs_id":"artificial_analysis:humanitys-last-exam:2bfdd17a-e027-4068-a54e-b0e90a6df118","organization":"Google","rank_in_source_response":450,"raw_value":"0.044","reported_by":"third_party","reported_date":"2025-03-12","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.044,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"ac48c49d-9e77-4394-ac4e-d1ee51fd5fee","model_name":"Gemini 1.5 Flash (May '24)","obs_id":"artificial_analysis:humanitys-last-exam:ac48c49d-9e77-4394-ac4e-d1ee51fd5fee","organization":"Google","rank_in_source_response":451,"raw_value":"0.0436","reported_by":"third_party","reported_date":"2024-05-14","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0436,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"dd738be7-2b69-4775-91a5-8851d3341c2d","model_name":"K2-V2 (medium)","obs_id":"artificial_analysis:humanitys-last-exam:dd738be7-2b69-4775-91a5-8851d3341c2d","organization":"MBZUAI Institute of Foundation Models","rank_in_source_response":452,"raw_value":"0.0435588507877665","reported_by":"third_party","reported_date":"2025-12-05","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0435588507877665,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"e8ffd75b-766f-4551-8c52-6e54706220eb","model_name":"Jamba 1.6 Mini","obs_id":"artificial_analysis:humanitys-last-exam:e8ffd75b-766f-4551-8c52-6e54706220eb","organization":"AI21 Labs","rank_in_source_response":453,"raw_value":"0.0431","reported_by":"third_party","reported_date":"2025-03-06","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0431,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"24ac5b00-5f03-4c47-8e37-522d1195383e","model_name":"Mistral Small 3.1","obs_id":"artificial_analysis:humanitys-last-exam:24ac5b00-5f03-4c47-8e37-522d1195383e","organization":"Mistral","rank_in_source_response":454,"raw_value":"0.0430954587581094","reported_by":"third_party","reported_date":"2025-03-17","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0430954587581094,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"26c0b5df-efa7-470f-a65e-2d883329e493","model_name":"Llama Nemotron Super 49B v1.5 (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:26c0b5df-efa7-470f-a65e-2d883329e493","organization":"NVIDIA","rank_in_source_response":454,"raw_value":"0.0430954587581094","reported_by":"third_party","reported_date":"2025-07-25","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0430954587581094,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"43da3718-3d6e-40dd-901a-05664179ff7f","model_name":"Mistral Small 3.2","obs_id":"artificial_analysis:humanitys-last-exam:43da3718-3d6e-40dd-901a-05664179ff7f","organization":"Mistral","rank_in_source_response":454,"raw_value":"0.0430954587581094","reported_by":"third_party","reported_date":"2025-06-20","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0430954587581094,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"7a7b52f6-fdef-4dae-9203-58c710ccc81d","model_name":"Mistral Saba","obs_id":"artificial_analysis:humanitys-last-exam:7a7b52f6-fdef-4dae-9203-58c710ccc81d","organization":"Mistral","rank_in_source_response":457,"raw_value":"0.043","reported_by":"third_party","reported_date":"2025-02-17","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.043,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"5c3dd927-48a3-4f3c-8045-9b135f62dfbb","model_name":"Nova Lite","obs_id":"artificial_analysis:humanitys-last-exam:5c3dd927-48a3-4f3c-8045-9b135f62dfbb","organization":"Amazon","rank_in_source_response":458,"raw_value":"0.0429","reported_by":"third_party","reported_date":"2024-12-03","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0429,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"3ef6db79-1dfa-4780-8c4b-affe2740d9ac","model_name":"Molmo2-8B","obs_id":"artificial_analysis:humanitys-last-exam:3ef6db79-1dfa-4780-8c4b-affe2740d9ac","organization":"Allen Institute for AI","rank_in_source_response":459,"raw_value":"0.0426320667284523","reported_by":"third_party","reported_date":"2025-12-11","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0426320667284523,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"9741f3c2-cbb1-4a3f-99ee-7bd7384d9038","model_name":"Ministral 3 8B","obs_id":"artificial_analysis:humanitys-last-exam:9741f3c2-cbb1-4a3f-99ee-7bd7384d9038","organization":"Mistral","rank_in_source_response":459,"raw_value":"0.0426320667284523","reported_by":"third_party","reported_date":"2025-12-02","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0426320667284523,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"ab7f016c-a29b-4710-bdf6-6a5cd96aacca","model_name":"NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:ab7f016c-a29b-4710-bdf6-6a5cd96aacca","organization":"NVIDIA","rank_in_source_response":459,"raw_value":"0.0426320667284523","reported_by":"third_party","reported_date":"2025-10-28","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0426320667284523,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"d034dafe-463d-4c50-956f-84fca657b26f","model_name":"Claude 4 Sonnet (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:d034dafe-463d-4c50-956f-84fca657b26f","organization":"Anthropic","rank_in_source_response":459,"raw_value":"0.0426320667284523","reported_by":"third_party","reported_date":"2025-05-22","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0426320667284523,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"b7726745-9c77-40c3-8452-974cb53d6fbc","model_name":"DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:b7726745-9c77-40c3-8452-974cb53d6fbc","organization":"Nous Research","rank_in_source_response":463,"raw_value":"0.0426","reported_by":"third_party","reported_date":"2025-02-13","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0426,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"bcca0e70-7e80-4c07-b1fa-b33bcfb19e51","model_name":"Gemini 2.0 Flash (Feb '25)","obs_id":"artificial_analysis:humanitys-last-exam:bcca0e70-7e80-4c07-b1fa-b33bcfb19e51","organization":"Google","rank_in_source_response":463,"raw_value":"0.0426","reported_by":"third_party","reported_date":"2025-02-05","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0426,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"7c045ca0-b331-488d-af31-df0fd331dfd1","model_name":"Mistral Small (Sep '24)","obs_id":"artificial_analysis:humanitys-last-exam:7c045ca0-b331-488d-af31-df0fd331dfd1","organization":"Mistral","rank_in_source_response":465,"raw_value":"0.0425","reported_by":"third_party","reported_date":"2024-09-17","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0425,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"c2b1e769-7aee-4669-8076-73918bdebf6c","model_name":"Claude 4.5 Haiku (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:c2b1e769-7aee-4669-8076-73918bdebf6c","organization":"Anthropic","rank_in_source_response":466,"raw_value":"0.0421686746987952","reported_by":"third_party","reported_date":"2025-10-15","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0421686746987952,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"d3968fd3-97d8-4693-8d26-19cefc6f5d5f","model_name":"Hermes 4 - Llama-3.1 405B (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:d3968fd3-97d8-4693-8d26-19cefc6f5d5f","organization":"Nous Research","rank_in_source_response":466,"raw_value":"0.0421686746987952","reported_by":"third_party","reported_date":"2025-08-27","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0421686746987952,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"fbc58677-e324-4b45-a979-7fd8eec555cd","model_name":"LFM2 24B A2B","obs_id":"artificial_analysis:humanitys-last-exam:fbc58677-e324-4b45-a979-7fd8eec555cd","organization":"Liquid AI","rank_in_source_response":466,"raw_value":"0.0421686746987952","reported_by":"third_party","reported_date":"2026-02-25","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0421686746987952,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"2e6400f5-85ca-4ebc-ba8f-c2811a631138","model_name":"Gemma 3 12B Instruct","obs_id":"artificial_analysis:humanitys-last-exam:2e6400f5-85ca-4ebc-ba8f-c2811a631138","organization":"Google","rank_in_source_response":469,"raw_value":"0.0421","reported_by":"third_party","reported_date":"2025-03-12","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0421,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"b5c1c91a-7474-4409-9a9c-9c2ac45d9eb6","model_name":"GPT-4o mini","obs_id":"artificial_analysis:humanitys-last-exam:b5c1c91a-7474-4409-9a9c-9c2ac45d9eb6","organization":"OpenAI","rank_in_source_response":470,"raw_value":"0.042","reported_by":"third_party","reported_date":"2024-07-18","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.042,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"43573c57-2403-46fb-af4b-a93de9a0c3f5","model_name":"Qwen3 235B A22B (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:43573c57-2403-46fb-af4b-a93de9a0c3f5","organization":"Qwen","rank_in_source_response":471,"raw_value":"0.0419","reported_by":"third_party","reported_date":"2025-04-28","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0419,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"7393c56a-ec31-48e9-b804-c04f2d2cb641","model_name":"Llama 3.1 Nemotron Instruct 70B","obs_id":"artificial_analysis:humanitys-last-exam:7393c56a-ec31-48e9-b804-c04f2d2cb641","organization":"NVIDIA","rank_in_source_response":471,"raw_value":"0.0419","reported_by":"third_party","reported_date":"2024-10-15","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0419,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"8ddacd41-bf43-411b-aa30-43ebf0567dd8","model_name":"Gemini 1.0 Pro","obs_id":"artificial_analysis:humanitys-last-exam:8ddacd41-bf43-411b-aa30-43ebf0567dd8","organization":"Google","rank_in_source_response":471,"raw_value":"0.0419","reported_by":"third_party","reported_date":"2023-12-06","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0419,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"3b608b70-6434-4baa-99ad-45d499703c67","model_name":"GPT-4.1","obs_id":"artificial_analysis:humanitys-last-exam:3b608b70-6434-4baa-99ad-45d499703c67","organization":"OpenAI","rank_in_source_response":474,"raw_value":"0.0418","reported_by":"third_party","reported_date":"2025-04-14","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0418,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"2cff73da-4855-403c-afc9-5540feadcc15","model_name":"Granite 3.3 8B (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:2cff73da-4855-403c-afc9-5540feadcc15","organization":"IBM","rank_in_source_response":475,"raw_value":"0.0417052826691381","reported_by":"third_party","reported_date":"2025-04-16","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0417052826691381,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"4928e950-7f37-4475-b0dc-c5bad781a321","model_name":"Mistral Large 3","obs_id":"artificial_analysis:humanitys-last-exam:4928e950-7f37-4475-b0dc-c5bad781a321","organization":"Mistral","rank_in_source_response":475,"raw_value":"0.0417052826691381","reported_by":"third_party","reported_date":"2025-12-02","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0417052826691381,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"a8c67863-9d66-44dd-8d27-f58654ecde03","model_name":"Gemma 3n E2B Instruct","obs_id":"artificial_analysis:humanitys-last-exam:a8c67863-9d66-44dd-8d27-f58654ecde03","organization":"Google","rank_in_source_response":475,"raw_value":"0.0417052826691381","reported_by":"third_party","reported_date":"2025-06-26","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0417052826691381,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"e58bbffd-fdc2-412a-b6d7-ca0e3f5d611a","model_name":"Nova Premier","obs_id":"artificial_analysis:humanitys-last-exam:e58bbffd-fdc2-412a-b6d7-ca0e3f5d611a","organization":"Amazon","rank_in_source_response":475,"raw_value":"0.0417052826691381","reported_by":"third_party","reported_date":"2025-04-30","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0417052826691381,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"d925845d-39ad-4de3-8495-f176b79828c0","model_name":"Claude 3.7 Sonnet (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:d925845d-39ad-4de3-8495-f176b79828c0","organization":"Anthropic","rank_in_source_response":479,"raw_value":"0.0416","reported_by":"third_party","reported_date":"2025-02-24","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0416,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"b26ff709-1773-4595-ae44-78e0a5bac29c","model_name":"DeepSeek R1 Distill Qwen 14B","obs_id":"artificial_analysis:humanitys-last-exam:b26ff709-1773-4595-ae44-78e0a5bac29c","organization":"DeepSeek","rank_in_source_response":480,"raw_value":"0.0413","reported_by":"third_party","reported_date":"2025-01-20","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0413,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"bf60740e-6aa5-422f-ba49-ef6e9d171205","model_name":"Qwen3 32B (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:bf60740e-6aa5-422f-ba49-ef6e9d171205","organization":"Qwen","rank_in_source_response":480,"raw_value":"0.0413","reported_by":"third_party","reported_date":"2025-04-28","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0413,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"d4be6393-8915-436c-a3a8-4e59bd5c89a9","model_name":"Granite 4.1 30B","obs_id":"artificial_analysis:humanitys-last-exam:d4be6393-8915-436c-a3a8-4e59bd5c89a9","organization":"IBM","rank_in_source_response":482,"raw_value":"0.041241890639481","reported_by":"third_party","reported_date":"2026-04-29","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.041241890639481,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"2443ac9e-a3db-423d-accb-8963f6fb0a53","model_name":"Grok 3","obs_id":"artificial_analysis:humanitys-last-exam:2443ac9e-a3db-423d-accb-8963f6fb0a53","organization":"xAI","rank_in_source_response":483,"raw_value":"0.0412","reported_by":"third_party","reported_date":"2025-02-19","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0412,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"352f834f-a03c-4117-8a29-c3ccd8a568ce","model_name":"Qwen2.5 Turbo","obs_id":"artificial_analysis:humanitys-last-exam:352f834f-a03c-4117-8a29-c3ccd8a568ce","organization":"Qwen","rank_in_source_response":484,"raw_value":"0.0409","reported_by":"third_party","reported_date":"2024-11-18","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0409,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"35d602fc-b8b8-4698-9f4d-f2ce11ca50e4","model_name":"Mistral Small (Feb '24)","obs_id":"artificial_analysis:humanitys-last-exam:35d602fc-b8b8-4698-9f4d-f2ce11ca50e4","organization":"Mistral","rank_in_source_response":484,"raw_value":"0.0409","reported_by":"third_party","reported_date":"2024-02-26","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0409,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"3de55b83-e02b-412e-8211-315bbebe3e94","model_name":"Gemini 2.0 Flash-Lite (Preview)","obs_id":"artificial_analysis:humanitys-last-exam:3de55b83-e02b-412e-8211-315bbebe3e94","organization":"Google","rank_in_source_response":484,"raw_value":"0.0409","reported_by":"third_party","reported_date":"2025-02-05","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0409,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"ecc6524a-d521-458a-8327-5009e8ce6549","model_name":"Qwen3 14B (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:ecc6524a-d521-458a-8327-5009e8ce6549","organization":"Qwen","rank_in_source_response":484,"raw_value":"0.0409","reported_by":"third_party","reported_date":"2025-04-28","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0409,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"1fc54cef-d179-48b1-a27d-046874e9b208","model_name":"Claude 3 Haiku","obs_id":"artificial_analysis:humanitys-last-exam:1fc54cef-d179-48b1-a27d-046874e9b208","organization":"Anthropic","rank_in_source_response":488,"raw_value":"0.0407784986098239","reported_by":"third_party","reported_date":"2024-03-04","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0407784986098239,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"c298d1a8-606c-4971-8613-ccdaaf941043","model_name":"GPT-5.4 nano (Non-Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:c298d1a8-606c-4971-8613-ccdaaf941043","organization":"OpenAI","rank_in_source_response":488,"raw_value":"0.0407784986098239","reported_by":"third_party","reported_date":"2026-03-17","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0407784986098239,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"b4ddb4c8-1400-44ab-8c2b-e2472088e7ff","model_name":"Jamba 1.5 Large","obs_id":"artificial_analysis:humanitys-last-exam:b4ddb4c8-1400-44ab-8c2b-e2472088e7ff","organization":"AI21 Labs","rank_in_source_response":490,"raw_value":"0.0407","reported_by":"third_party","reported_date":"2024-08-22","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0407,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"fddb72bd-60d3-41af-acc5-3df9a290eb8e","model_name":"Gemini 2.0 Flash (experimental)","obs_id":"artificial_analysis:humanitys-last-exam:fddb72bd-60d3-41af-acc5-3df9a290eb8e","organization":"Google","rank_in_source_response":490,"raw_value":"0.0407","reported_by":"third_party","reported_date":"2024-12-11","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0407,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"59e22326-1bca-4432-a5fa-147fbe8854e7","model_name":"Mistral Medium 3","obs_id":"artificial_analysis:humanitys-last-exam:59e22326-1bca-4432-a5fa-147fbe8854e7","organization":"Mistral","rank_in_source_response":492,"raw_value":"0.0405","reported_by":"third_party","reported_date":"2025-05-07","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0405,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"3bc32f13-5afa-4e28-bce1-10e57376686b","model_name":"Command A","obs_id":"artificial_analysis:humanitys-last-exam:3bc32f13-5afa-4e28-bce1-10e57376686b","organization":"Cohere","rank_in_source_response":493,"raw_value":"0.0403151065801668","reported_by":"third_party","reported_date":"2025-03-13","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0403151065801668,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"6fd796d3-f346-4f66-97df-5da81714fc73","model_name":"Nova 2.0 Lite (low)","obs_id":"artificial_analysis:humanitys-last-exam:6fd796d3-f346-4f66-97df-5da81714fc73","organization":"Amazon","rank_in_source_response":493,"raw_value":"0.0403151065801668","reported_by":"third_party","reported_date":"2025-10-29","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0403151065801668,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"cc1fa238-1a76-486d-a997-22309275eadd","model_name":"Devstral Small (May '25)","obs_id":"artificial_analysis:humanitys-last-exam:cc1fa238-1a76-486d-a997-22309275eadd","organization":"Mistral","rank_in_source_response":493,"raw_value":"0.0403151065801668","reported_by":"third_party","reported_date":"2025-05-21","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0403151065801668,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"ca6c1412-f3c1-4391-9231-f83a702aa7af","model_name":"Mixtral 8x22B Instruct","obs_id":"artificial_analysis:humanitys-last-exam:ca6c1412-f3c1-4391-9231-f83a702aa7af","organization":"Mistral","rank_in_source_response":496,"raw_value":"0.0401","reported_by":"third_party","reported_date":"2024-04-17","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0401,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"1d0db5a3-3132-4213-a94b-c2e395d08283","model_name":"Qwen2.5 Instruct 32B","obs_id":"artificial_analysis:humanitys-last-exam:1d0db5a3-3132-4213-a94b-c2e395d08283","organization":"Qwen","rank_in_source_response":497,"raw_value":"0.0399","reported_by":"third_party","reported_date":"2024-09-19","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0399,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"1dcea4f7-7e8b-49f8-abe2-5860ff9f349e","model_name":"Hermes 3 - Llama-3.1 70B","obs_id":"artificial_analysis:humanitys-last-exam:1dcea4f7-7e8b-49f8-abe2-5860ff9f349e","organization":"Nous Research","rank_in_source_response":497,"raw_value":"0.0399","reported_by":"third_party","reported_date":"2024-08-15","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0399,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"05e45a36-b5c6-47a1-8adb-9ddc19add5b3","model_name":"GPT-5 nano (minimal)","obs_id":"artificial_analysis:humanitys-last-exam:05e45a36-b5c6-47a1-8adb-9ddc19add5b3","organization":"OpenAI","rank_in_source_response":499,"raw_value":"0.0398517145505097","reported_by":"third_party","reported_date":"2025-08-07","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0398517145505097,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"45c87531-2d57-48e0-8012-202cd636189e","model_name":"Llama 3.1 Instruct 405B","obs_id":"artificial_analysis:humanitys-last-exam:45c87531-2d57-48e0-8012-202cd636189e","organization":"Meta","rank_in_source_response":500,"raw_value":"0.0398","reported_by":"third_party","reported_date":"2024-07-23","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0398,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"575498d6-60ec-466b-9372-fea19911fd07","model_name":"GPT-4o (March 2025, chatgpt-4o-latest)","obs_id":"artificial_analysis:humanitys-last-exam:575498d6-60ec-466b-9372-fea19911fd07","organization":"OpenAI","rank_in_source_response":501,"raw_value":"0.0397","reported_by":"third_party","reported_date":"2025-03-27","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0397,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"a20ae33a-46e1-41e6-81a0-fe8b00d2e538","model_name":"Nova 2.0 Pro Preview (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:a20ae33a-46e1-41e6-81a0-fe8b00d2e538","organization":"Amazon","rank_in_source_response":502,"raw_value":"0.0393883225208526","reported_by":"third_party","reported_date":"2025-11-27","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0393883225208526,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"8823351e-8232-4c9c-8a1d-cd2c1d2c1196","model_name":"QwQ 32B-Preview","obs_id":"artificial_analysis:humanitys-last-exam:8823351e-8232-4c9c-8a1d-cd2c1d2c1196","organization":"Qwen","rank_in_source_response":503,"raw_value":"0.0391","reported_by":"third_party","reported_date":"2024-11-27","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0391,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"9dba61f5-78ee-4190-8d1d-8e7063ffd386","model_name":"Qwen3 8B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:9dba61f5-78ee-4190-8d1d-8e7063ffd386","organization":"Qwen","rank_in_source_response":504,"raw_value":"0.0389","reported_by":"third_party","reported_date":"2025-04-28","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0389,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"9e141c0d-fc82-4e07-bb2e-fe0003bc030b","model_name":"Claude 2.1","obs_id":"artificial_analysis:humanitys-last-exam:9e141c0d-fc82-4e07-bb2e-fe0003bc030b","organization":"Anthropic","rank_in_source_response":504,"raw_value":"0.0389","reported_by":"third_party","reported_date":"2023-11-21","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0389,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"1f6478c9-3e22-4586-adbe-841782859677","model_name":"Nova 2.0 Omni (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:1f6478c9-3e22-4586-adbe-841782859677","organization":"Amazon","rank_in_source_response":506,"raw_value":"0.0384615384615385","reported_by":"third_party","reported_date":"2025-11-26","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0384615384615385,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"da9fe224-8af3-46d7-a8c4-6220779c3f35","model_name":"Qwen3 Coder 30B A3B Instruct","obs_id":"artificial_analysis:humanitys-last-exam:da9fe224-8af3-46d7-a8c4-6220779c3f35","organization":"Qwen","rank_in_source_response":506,"raw_value":"0.0384615384615385","reported_by":"third_party","reported_date":"2025-07-31","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0384615384615385,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"dec8073c-57e2-41c0-b1aa-7a62960f103f","model_name":"Qwen3 VL 8B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:dec8073c-57e2-41c0-b1aa-7a62960f103f","organization":"Qwen","rank_in_source_response":506,"raw_value":"0.0384615384615385","reported_by":"third_party","reported_date":"2025-10-14","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0384615384615385,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"b9dc72c6-7bea-4936-a55a-4b0c835fc755","model_name":"Qwen2.5 Max","obs_id":"artificial_analysis:humanitys-last-exam:b9dc72c6-7bea-4936-a55a-4b0c835fc755","organization":"Qwen","rank_in_source_response":509,"raw_value":"0.0382","reported_by":"third_party","reported_date":"2025-01-28","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0382,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"c4c3b42f-e0f0-48ca-b6f9-b296e7697806","model_name":"Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:c4c3b42f-e0f0-48ca-b6f9-b296e7697806","organization":"NVIDIA","rank_in_source_response":510,"raw_value":"0.0381","reported_by":"third_party","reported_date":"2025-03-18","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0381,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"55a3ebf6-6117-4cc1-8596-c6de6e552fd4","model_name":"Gemini 2.5 Flash Preview (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:55a3ebf6-6117-4cc1-8596-c6de6e552fd4","organization":"Google","rank_in_source_response":511,"raw_value":"0.038","reported_by":"third_party","reported_date":"2025-04-17","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.038,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"12f6a061-0ab3-4c76-b225-49abee253651","model_name":"Mistral Small 4 (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:12f6a061-0ab3-4c76-b225-49abee253651","organization":"Mistral","rank_in_source_response":512,"raw_value":"0.0379981464318814","reported_by":"third_party","reported_date":"2026-03-16","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0379981464318814,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"5dba8d07-9992-483c-81db-dac97cb15ba8","model_name":"Granite 4.0 H Small","obs_id":"artificial_analysis:humanitys-last-exam:5dba8d07-9992-483c-81db-dac97cb15ba8","organization":"IBM","rank_in_source_response":512,"raw_value":"0.0379981464318814","reported_by":"third_party","reported_date":"2025-09-22","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0379981464318814,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"82ed9bd2-c97b-4c35-9312-94bb72001e36","model_name":"Granite 4.1 8B","obs_id":"artificial_analysis:humanitys-last-exam:82ed9bd2-c97b-4c35-9312-94bb72001e36","organization":"IBM","rank_in_source_response":512,"raw_value":"0.0379981464318814","reported_by":"third_party","reported_date":"2026-04-29","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0379981464318814,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"adf9a85e-abc3-4f28-937b-db6655cc5238","model_name":"Llama 4 Scout","obs_id":"artificial_analysis:humanitys-last-exam:adf9a85e-abc3-4f28-937b-db6655cc5238","organization":"Meta","rank_in_source_response":515,"raw_value":"0.0378","reported_by":"third_party","reported_date":"2025-04-05","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0378,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"a8efb564-9d17-4d7f-8f43-e9110657ce21","model_name":"DeepHermes 3 - Mistral 24B Preview (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:a8efb564-9d17-4d7f-8f43-e9110657ce21","organization":"Nous Research","rank_in_source_response":516,"raw_value":"0.0376","reported_by":"third_party","reported_date":"2025-03-13","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0376,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"e5dd499f-c330-45ec-9ff0-a99209c82af7","model_name":"Mistral Small 3","obs_id":"artificial_analysis:humanitys-last-exam:e5dd499f-c330-45ec-9ff0-a99209c82af7","organization":"Mistral","rank_in_source_response":516,"raw_value":"0.0376","reported_by":"third_party","reported_date":"2025-01-30","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0376,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"ee708f92-374e-4123-b900-e22d7b2afc19","model_name":"Phi-4","obs_id":"artificial_analysis:humanitys-last-exam:ee708f92-374e-4123-b900-e22d7b2afc19","organization":"Microsoft","rank_in_source_response":516,"raw_value":"0.0376","reported_by":"third_party","reported_date":"2024-12-12","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0376,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"72c358fd-7d45-4d68-89aa-699743710924","model_name":"GPT-4.1 nano","obs_id":"artificial_analysis:humanitys-last-exam:72c358fd-7d45-4d68-89aa-699743710924","organization":"OpenAI","rank_in_source_response":519,"raw_value":"0.0375347544022243","reported_by":"third_party","reported_date":"2025-04-14","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0375347544022243,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"9eae4ec4-61b8-48bc-9843-3edd506ae933","model_name":"Devstral Small (Jul '25)","obs_id":"artificial_analysis:humanitys-last-exam:9eae4ec4-61b8-48bc-9843-3edd506ae933","organization":"Mistral","rank_in_source_response":519,"raw_value":"0.0375347544022243","reported_by":"third_party","reported_date":"2025-07-10","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0375347544022243,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"aba82268-2bb7-4a0f-80be-9b7722e2145b","model_name":"Devstral Medium","obs_id":"artificial_analysis:humanitys-last-exam:aba82268-2bb7-4a0f-80be-9b7722e2145b","organization":"Mistral","rank_in_source_response":519,"raw_value":"0.0375347544022243","reported_by":"third_party","reported_date":"2025-07-10","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0375347544022243,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"d80eb0f1-f62e-4d31-99d2-7a925eb126b0","model_name":"Gemma 4 E4B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:d80eb0f1-f62e-4d31-99d2-7a925eb126b0","organization":"Google","rank_in_source_response":519,"raw_value":"0.0375347544022243","reported_by":"third_party","reported_date":"2026-04-03","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0375347544022243,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"f78138d6-2e04-4a84-919a-20d177cb6ff1","model_name":"Jamba Reasoning 3B","obs_id":"artificial_analysis:humanitys-last-exam:f78138d6-2e04-4a84-919a-20d177cb6ff1","organization":"AI21 Labs","rank_in_source_response":519,"raw_value":"0.0375347544022243","reported_by":"third_party","reported_date":"2025-10-08","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0375347544022243,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"44db6283-aa82-4799-af4a-679fe0530845","model_name":"Solar Pro 2 (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:44db6283-aa82-4799-af4a-679fe0530845","organization":"Upstage","rank_in_source_response":524,"raw_value":"0.0370713623725672","reported_by":"third_party","reported_date":"2025-07-09","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0370713623725672,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"0a603978-03b9-4f47-a273-2f7fd969be85","model_name":"Claude 3.5 Sonnet (Oct '24)","obs_id":"artificial_analysis:humanitys-last-exam:0a603978-03b9-4f47-a273-2f7fd969be85","organization":"Anthropic","rank_in_source_response":525,"raw_value":"0.0369","reported_by":"third_party","reported_date":"2024-10-22","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0369,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"1d81aa1c-64c8-442a-9c41-81b37e407b91","model_name":"Gemini 2.5 Flash-Lite (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:1d81aa1c-64c8-442a-9c41-81b37e407b91","organization":"Google","rank_in_source_response":526,"raw_value":"0.0366079703429101","reported_by":"third_party","reported_date":"2025-06-17","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0366079703429101,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"43098bd0-77ca-408b-b698-9d60b1d1c3b8","model_name":"GLM-4.6V (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:43098bd0-77ca-408b-b698-9d60b1d1c3b8","organization":"Z.ai","rank_in_source_response":526,"raw_value":"0.0366079703429101","reported_by":"third_party","reported_date":"2025-12-08","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0366079703429101,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"432d6c36-8825-47f3-b4eb-58529cea346b","model_name":"Solar Pro 2 (Preview) (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:432d6c36-8825-47f3-b4eb-58529cea346b","organization":"Upstage","rank_in_source_response":526,"raw_value":"0.0366079703429101","reported_by":"third_party","reported_date":"2025-05-20","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0366079703429101,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"78452c64-7303-4192-bca5-2d9ec5c623d4","model_name":"Jamba 1.7 Large","obs_id":"artificial_analysis:humanitys-last-exam:78452c64-7303-4192-bca5-2d9ec5c623d4","organization":"AI21 Labs","rank_in_source_response":526,"raw_value":"0.0366079703429101","reported_by":"third_party","reported_date":"2025-07-07","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0366079703429101,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"7656c62b-5345-435b-bf12-b6ce2ca0d58d","model_name":"Qwen2 Instruct 72B","obs_id":"artificial_analysis:humanitys-last-exam:7656c62b-5345-435b-bf12-b6ce2ca0d58d","organization":"Qwen","rank_in_source_response":530,"raw_value":"0.0366","reported_by":"third_party","reported_date":"2024-06-07","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0366,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"033e4aa9-a556-4224-87b0-341ed1070257","model_name":"Claude 3.5 Haiku","obs_id":"artificial_analysis:humanitys-last-exam:033e4aa9-a556-4224-87b0-341ed1070257","organization":"Anthropic","rank_in_source_response":531,"raw_value":"0.0363","reported_by":"third_party","reported_date":"2024-10-22","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0363,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"b2e68f0a-8f66-4e4c-9821-2b786cea601b","model_name":"Claude 3 Sonnet","obs_id":"artificial_analysis:humanitys-last-exam:b2e68f0a-8f66-4e4c-9821-2b786cea601b","organization":"Anthropic","rank_in_source_response":532,"raw_value":"0.0362","reported_by":"third_party","reported_date":"2024-03-04","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0362,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"04781a0e-40f0-4e2a-a4e5-18e389364a79","model_name":"Gemma 3 270M","obs_id":"artificial_analysis:humanitys-last-exam:04781a0e-40f0-4e2a-a4e5-18e389364a79","organization":"Google","rank_in_source_response":533,"raw_value":"0.036144578313253","reported_by":"third_party","reported_date":"2025-08-14","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.036144578313253,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"54442579-2a4d-40cc-b264-bc4ff29e311a","model_name":"OLMo 2 32B","obs_id":"artificial_analysis:humanitys-last-exam:54442579-2a4d-40cc-b264-bc4ff29e311a","organization":"Allen Institute for AI","rank_in_source_response":533,"raw_value":"0.036144578313253","reported_by":"third_party","reported_date":"2025-03-13","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.036144578313253,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"dae31abc-0587-44d0-ba53-f78e96b6e486","model_name":"K2-V2 (low)","obs_id":"artificial_analysis:humanitys-last-exam:dae31abc-0587-44d0-ba53-f78e96b6e486","organization":"MBZUAI Institute of Foundation Models","rank_in_source_response":533,"raw_value":"0.036144578313253","reported_by":"third_party","reported_date":"2025-12-05","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.036144578313253,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"f5d83128-047f-496d-ba49-8a428abe8345","model_name":"Qwen3 VL 4B Instruct","obs_id":"artificial_analysis:humanitys-last-exam:f5d83128-047f-496d-ba49-8a428abe8345","organization":"Qwen","rank_in_source_response":533,"raw_value":"0.036144578313253","reported_by":"third_party","reported_date":"2025-10-14","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.036144578313253,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"92b19c88-fa87-4595-957e-fe9aa5fa5ad4","model_name":"Jamba 1.6 Large","obs_id":"artificial_analysis:humanitys-last-exam:92b19c88-fa87-4595-957e-fe9aa5fa5ad4","organization":"AI21 Labs","rank_in_source_response":537,"raw_value":"0.0361","reported_by":"third_party","reported_date":"2025-03-06","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0361,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"b515503d-4d65-4a3f-8a4a-6c731e2b079f","model_name":"o1-mini","obs_id":"artificial_analysis:humanitys-last-exam:b515503d-4d65-4a3f-8a4a-6c731e2b079f","organization":"OpenAI","rank_in_source_response":538,"raw_value":"0.0357","reported_by":"third_party","reported_date":"2024-09-12","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0357,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"09f43999-b67b-4c1b-b050-44df41ed7e62","model_name":"Devstral 2","obs_id":"artificial_analysis:humanitys-last-exam:09f43999-b67b-4c1b-b050-44df41ed7e62","organization":"Mistral","rank_in_source_response":539,"raw_value":"0.0356811862835959","reported_by":"third_party","reported_date":"2025-12-09","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0356811862835959,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"235060f4-057d-4bd1-8b8e-4a92908c770e","model_name":"Hermes 4 - Llama-3.1 70B (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:235060f4-057d-4bd1-8b8e-4a92908c770e","organization":"Nous Research","rank_in_source_response":539,"raw_value":"0.0356811862835959","reported_by":"third_party","reported_date":"2025-08-27","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0356811862835959,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"976cc8ad-7904-4056-83c5-960181f47d5f","model_name":"Llama 3.3 Instruct 70B","obs_id":"artificial_analysis:humanitys-last-exam:976cc8ad-7904-4056-83c5-960181f47d5f","organization":"Meta","rank_in_source_response":541,"raw_value":"0.0356","reported_by":"third_party","reported_date":"2024-12-06","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0356,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"b4f7d7a4-869a-4ee7-b17a-4046cd1e79fd","model_name":"Qwen2.5 Instruct 72B","obs_id":"artificial_analysis:humanitys-last-exam:b4f7d7a4-869a-4ee7-b17a-4046cd1e79fd","organization":"Qwen","rank_in_source_response":541,"raw_value":"0.0356","reported_by":"third_party","reported_date":"2024-09-19","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0356,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"83cb898e-05d9-4e4b-9de3-2d305014d923","model_name":"Claude Instant","obs_id":"artificial_analysis:humanitys-last-exam:83cb898e-05d9-4e4b-9de3-2d305014d923","organization":"Anthropic","rank_in_source_response":543,"raw_value":"0.0353","reported_by":"third_party","reported_date":"2023-03-14","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0353,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"04586102-6a28-48f8-a82e-85775d7ed779","model_name":"Qwen2.5 Coder Instruct 32B","obs_id":"artificial_analysis:humanitys-last-exam:04586102-6a28-48f8-a82e-85775d7ed779","organization":"Qwen","rank_in_source_response":544,"raw_value":"0.0351","reported_by":"third_party","reported_date":"2024-11-11","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0351,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"1f05af98-1ec6-4506-a0b8-57a8c9b63878","model_name":"Mistral Medium","obs_id":"artificial_analysis:humanitys-last-exam:1f05af98-1ec6-4506-a0b8-57a8c9b63878","organization":"Mistral","rank_in_source_response":544,"raw_value":"0.0351","reported_by":"third_party","reported_date":"2023-12-11","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0351,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"5e4e4590-a77e-4b66-95f8-f3960a1a7c68","model_name":"Mistral Large (Feb '24)","obs_id":"artificial_analysis:humanitys-last-exam:5e4e4590-a77e-4b66-95f8-f3960a1a7c68","organization":"Mistral","rank_in_source_response":546,"raw_value":"0.035","reported_by":"third_party","reported_date":"2024-02-26","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.035,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"16f2578b-1b28-4be3-b371-700c2677bcd6","model_name":"Gemini 1.5 Pro (May '24)","obs_id":"artificial_analysis:humanitys-last-exam:16f2578b-1b28-4be3-b371-700c2677bcd6","organization":"Google","rank_in_source_response":547,"raw_value":"0.0348","reported_by":"third_party","reported_date":"2024-05-15","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0348,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"0081ab31-d10a-44a0-a10d-eee5533fec65","model_name":"GLM-4.5V (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:0081ab31-d10a-44a0-a10d-eee5533fec65","organization":"Z.ai","rank_in_source_response":548,"raw_value":"0.0347544022242817","reported_by":"third_party","reported_date":"2025-08-11","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0347544022242817,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"ce819310-af7c-49d3-9a02-6845111e1788","model_name":"Devstral Small 2","obs_id":"artificial_analysis:humanitys-last-exam:ce819310-af7c-49d3-9a02-6845111e1788","organization":"Mistral","rank_in_source_response":548,"raw_value":"0.0347544022242817","reported_by":"third_party","reported_date":"2025-12-09","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0347544022242817,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"91e3b45f-3f52-4511-8c15-8948854bebc5","model_name":"Granite 4.1 3B","obs_id":"artificial_analysis:humanitys-last-exam:91e3b45f-3f52-4511-8c15-8948854bebc5","organization":"IBM","rank_in_source_response":550,"raw_value":"0.0342910101946247","reported_by":"third_party","reported_date":"2026-04-29","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0342910101946247,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"7b269763-ecc0-41ef-aa29-47ef632ac065","model_name":"Gemini 2.0 Flash-Lite (Feb '25)","obs_id":"artificial_analysis:humanitys-last-exam:7b269763-ecc0-41ef-aa29-47ef632ac065","organization":"Google","rank_in_source_response":551,"raw_value":"0.0335","reported_by":"third_party","reported_date":"2025-02-25","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0335,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"50f92d5f-f413-4c97-8dab-331101622a28","model_name":"Mistral Large 2 (Nov '24)","obs_id":"artificial_analysis:humanitys-last-exam:50f92d5f-f413-4c97-8dab-331101622a28","organization":"Mistral","rank_in_source_response":552,"raw_value":"0.0334","reported_by":"third_party","reported_date":"2024-11-18","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0334,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"ae4fe623-80ab-4ea3-8921-70a18ea0fc7e","model_name":"ERNIE 4.5 300B A47B","obs_id":"artificial_analysis:humanitys-last-exam:ae4fe623-80ab-4ea3-8921-70a18ea0fc7e","organization":"Baidu","rank_in_source_response":553,"raw_value":"0.0333642261353105","reported_by":"third_party","reported_date":"2025-06-30","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0333642261353105,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"e46198a7-cd29-4afd-933d-cdf180f0f305","model_name":"Qwen3 4B (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:e46198a7-cd29-4afd-933d-cdf180f0f305","organization":"Qwen","rank_in_source_response":554,"raw_value":"0.0332","reported_by":"third_party","reported_date":"2025-04-28","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0332,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"f73f4711-9c61-40a7-a258-b71c14727f53","model_name":"Llama 3.1 Tulu3 405B","obs_id":"artificial_analysis:humanitys-last-exam:f73f4711-9c61-40a7-a258-b71c14727f53","organization":"Allen Institute for AI","rank_in_source_response":555,"raw_value":"0.0328","reported_by":"third_party","reported_date":"2025-01-30","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0328,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"aca9c1ad-fc86-49f3-a312-b1e517ea100c","model_name":"Claude 3.5 Sonnet (June '24)","obs_id":"artificial_analysis:humanitys-last-exam:aca9c1ad-fc86-49f3-a312-b1e517ea100c","organization":"Anthropic","rank_in_source_response":556,"raw_value":"0.0323","reported_by":"third_party","reported_date":"2024-06-21","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0323,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"546ec53f-273c-4af7-b13f-b88c41f45905","model_name":"Nova Pro","obs_id":"artificial_analysis:humanitys-last-exam:546ec53f-273c-4af7-b13f-b88c41f45905","organization":"Amazon","rank_in_source_response":557,"raw_value":"0.0319","reported_by":"third_party","reported_date":"2024-12-03","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0319,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"41faf421-118b-465b-b170-d200776580d1","model_name":"Gemini 1.5 Flash (Sep '24)","obs_id":"artificial_analysis:humanitys-last-exam:41faf421-118b-465b-b170-d200776580d1","organization":"Google","rank_in_source_response":558,"raw_value":"0.0317","reported_by":"third_party","reported_date":"2024-09-24","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0317,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"76aa6af5-fdc6-4739-a300-983f14e74a67","model_name":"GPT-4 Turbo","obs_id":"artificial_analysis:humanitys-last-exam:76aa6af5-fdc6-4739-a300-983f14e74a67","organization":"OpenAI","rank_in_source_response":559,"raw_value":"0.0313","reported_by":"third_party","reported_date":"2023-11-06","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0313,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"34ef2b5c-3df3-437e-b9c5-81346f8c14a8","model_name":"Sarvam M (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:34ef2b5c-3df3-437e-b9c5-81346f8c14a8","organization":"Sarvam","rank_in_source_response":560,"raw_value":"0.031047265987025","reported_by":"third_party","reported_date":"2025-05-23","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.031047265987025,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"444cdb1e-bab8-42cd-938c-b2d7a93e2da1","model_name":"DeepSeek R1 Distill Qwen 1.5B","obs_id":"artificial_analysis:humanitys-last-exam:444cdb1e-bab8-42cd-938c-b2d7a93e2da1","organization":"DeepSeek","rank_in_source_response":561,"raw_value":"0.0308","reported_by":"third_party","reported_date":"2025-01-20","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0308,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"291a510a-dcc0-40df-8a80-b3aa31900a6c","model_name":"Grok 2 (Dec '24)","obs_id":"artificial_analysis:humanitys-last-exam:291a510a-dcc0-40df-8a80-b3aa31900a6c","organization":"xAI","rank_in_source_response":562,"raw_value":"0.0306","reported_by":"third_party","reported_date":"2024-12-12","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0306,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"1b05e346-e86a-4a20-8feb-7da8c65a99aa","model_name":"Mistral Large 2 (Jul '24)","obs_id":"artificial_analysis:humanitys-last-exam:1b05e346-e86a-4a20-8feb-7da8c65a99aa","organization":"Mistral","rank_in_source_response":563,"raw_value":"0.0295","reported_by":"third_party","reported_date":"2024-07-24","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0295,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"1cb96708-f6c1-4668-9804-5db6ecac01ed","model_name":"DBRX Instruct","obs_id":"artificial_analysis:humanitys-last-exam:1cb96708-f6c1-4668-9804-5db6ecac01ed","organization":"Databricks","rank_in_source_response":564,"raw_value":"0.0292","reported_by":"third_party","reported_date":"2024-03-27","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0292,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"43fc5506-c5ed-4dee-9b85-962bf7ae3986","model_name":"DeepSeek V3 (Dec '24)","obs_id":"artificial_analysis:humanitys-last-exam:43fc5506-c5ed-4dee-9b85-962bf7ae3986","organization":"DeepSeek","rank_in_source_response":565,"raw_value":"0.029","reported_by":"third_party","reported_date":"2024-12-26","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.029,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"76bce7fb-3a3f-4b66-a78d-35ccf3edf5d2","model_name":"Nova 2.0 Lite (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:76bce7fb-3a3f-4b66-a78d-35ccf3edf5d2","organization":"Amazon","rank_in_source_response":566,"raw_value":"0.0287303058387396","reported_by":"third_party","reported_date":"2025-10-29","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0287303058387396,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"de0beaf0-c951-487a-8eb4-3dd12e74122c","model_name":"Pixtral Large","obs_id":"artificial_analysis:humanitys-last-exam:de0beaf0-c951-487a-8eb4-3dd12e74122c","organization":"Mistral","rank_in_source_response":567,"raw_value":"0.028","reported_by":"third_party","reported_date":"2024-11-18","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.028,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"7829427f-f0e3-4f6d-a228-5fbf70dacc02","model_name":"Claude 3 Opus","obs_id":"artificial_analysis:humanitys-last-exam:7829427f-f0e3-4f6d-a228-5fbf70dacc02","organization":"Anthropic","rank_in_source_response":568,"raw_value":"0.0275","reported_by":"third_party","reported_date":"2024-03-04","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0275,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"b4784397-aa28-411b-b011-9c4331bfa9c8","model_name":"GPT-4o (ChatGPT)","obs_id":"artificial_analysis:humanitys-last-exam:b4784397-aa28-411b-b011-9c4331bfa9c8","organization":"OpenAI","rank_in_source_response":569,"raw_value":"0.0273","reported_by":"third_party","reported_date":"2025-02-15","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0273,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"3cf875b8-b6b5-42c0-ad70-617d5be59d00","model_name":"Qwen3 VL 8B Instruct","obs_id":"artificial_analysis:humanitys-last-exam:3cf875b8-b6b5-42c0-ad70-617d5be59d00","organization":"Qwen","rank_in_source_response":570,"raw_value":"0.0268767377201112","reported_by":"third_party","reported_date":"2025-10-14","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0268767377201112,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"5d4acc80-7a88-4e84-bfe7-99071b84e6a4","model_name":"Qwen3.5 2B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:5d4acc80-7a88-4e84-bfe7-99071b84e6a4","organization":"Qwen","rank_in_source_response":571,"raw_value":"0.025949953660797","reported_by":"third_party","reported_date":"2026-03-02","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.025949953660797,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"598de97d-029e-47b6-96ec-dbc1e0f9045a","model_name":"Kimi Linear 48B A3B Instruct","obs_id":"artificial_analysis:humanitys-last-exam:598de97d-029e-47b6-96ec-dbc1e0f9045a","organization":"Moonshot AI","rank_in_source_response":572,"raw_value":"0.0245597775718258","reported_by":"third_party","reported_date":"2025-10-30","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0245597775718258,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"c1045dc0-4fd3-4adb-9548-18763e0d051f","model_name":"GPT-4o (Nov '24)","obs_id":"artificial_analysis:humanitys-last-exam:c1045dc0-4fd3-4adb-9548-18763e0d051f","organization":"OpenAI","rank_in_source_response":573,"raw_value":"0.0242","reported_by":"third_party","reported_date":"2024-11-20","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0242,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"8c1be908-67b6-4cf4-ba08-83ddbe44fde3","model_name":"GPT-4o (Aug '24)","obs_id":"artificial_analysis:humanitys-last-exam:8c1be908-67b6-4cf4-ba08-83ddbe44fde3","organization":"OpenAI","rank_in_source_response":574,"raw_value":"0.0233","reported_by":"third_party","reported_date":"2024-08-06","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0233,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"b2dd592a-fbc5-458a-b26d-f3964cbab82f","model_name":"Qwen3 8B (Non-reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:b2dd592a-fbc5-458a-b26d-f3964cbab82f","organization":"Qwen","rank_in_source_response":575,"raw_value":"0.0195","reported_by":"third_party","reported_date":"2025-04-28","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0195,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"e98e911e-9fb2-4a9a-826e-3d681d0cdca8","model_name":"GPT-4o (May '24)","obs_id":"artificial_analysis:humanitys-last-exam:e98e911e-9fb2-4a9a-826e-3d681d0cdca8","organization":"OpenAI","rank_in_source_response":576,"raw_value":"0.0176","reported_by":"third_party","reported_date":"2024-05-13","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0176,"value_kind":"number"},{"comparable_group":null,"crawled_at":"2026-08-25T10:41:06Z","date_precision":"model_announcement","document_id":"artificial_analysis:https://artificialanalysis.ai/evaluations/humanitys-last-exam","key":"artificial-analysis:humanitys-last-exam","measured_by":"Artificial Analysis","model_id":"a6ea7ec0-0aca-4442-98fb-4296c6d18b31","model_name":"Qwen3.5 0.8B (Reasoning)","obs_id":"artificial_analysis:humanitys-last-exam:a6ea7ec0-0aca-4442-98fb-4296c6d18b31","organization":"Qwen","rank_in_source_response":577,"raw_value":"0.0106580166821131","reported_by":"third_party","reported_date":"2026-03-02","series_id":"artificial_analysis:humanitys-last-exam:default","source":"artificial_analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","value":0.0106580166821131,"value_kind":"number"}],"series":{"bounds":{"basis":"aggregator_declared","max":null,"min":null},"declared_max":null,"direction":"higher_is_better","direction_basis":"source_rank_descending","display_scale":null,"first_score_record":{"date_precision":"model_announcement","obs_id":"artificial_analysis:humanitys-last-exam:83cb898e-05d9-4e4b-9de3-2d305014d923","reported_at":"2023-03-14","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam"},"first_score_report":null,"key":"artificial-analysis:humanitys-last-exam","max_score_contradicted":false,"metric":null,"observation_count":577,"observed_max":0.554680259499537,"score_summary":{"display_max":55.468025949953706,"display_multiplier":100,"model_count":577,"model_count_basis":"source_model_id","numeric_count":577,"raw_max":0.554680259499537,"raw_min":0.0106580166821131,"source_reference":{"crawled_at":"2026-08-25T10:41:06Z","obs_id":"artificial_analysis:humanitys-last-exam:cd55210d-358e-4df1-ba9c-9acb5f186cc9","reported_date":"2026-06-09","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam"},"unit":null},"series_id":"artificial_analysis:humanitys-last-exam:default"}}},"siblings":[]},"presentation":{"record":{"categories":["intelligence-index","reasoning","knowledge"],"collected_at":"2026-08-25T10:41:06Z","has_dataset":false,"has_paper":false,"has_repo":false,"key":"artificial-analysis:humanitys-last-exam","name":"Humanity’s Last Exam","score_count":577,"slug":"artificial-analysis-humanitys-last-exam","source":"artificial_analysis","topics":["reasoning-math"],"descriptions":{"en":"Reasoning & knowledge"},"editorial_guide":{"id":"artificial-analysis-humanitys-last-exam","title":"Humanity’s Last Exam · Artificial Analysis"}},"evidence_html":{"en":"<section class=\"publication-sources prose\"><h2>Original publication</h2><p>Original Humanity’s Last Exam publications for this Artificial Analysis source record. Scores remain the separately collected Artificial Analysis snapshot from 25 August 2026; later publication and dataset revisions do not establish the setup of every saved evaluation.</p><p class=\"evidence-note\">Reviewed 2026-10-29</p><ul><li><a href=\"https://lastexam.ai/\">Official project · Humanity’s Last Exam · original project</a></li><li><a href=\"https://arxiv.org/abs/2501.14249\">Original paper · Humanity’s Last Exam · original paper and version history</a></li><li><a href=\"https://huggingface.co/datasets/cais/hle\">Official dataset · Humanity’s Last Exam · official dataset</a></li><li><a href=\"https://github.com/centerforaisafety/hle\">Official repository · Humanity’s Last Exam · official evaluation repository</a></li></ul></section><section class=\"record-evidence prose\"><h2>Evidence available for this benchmark</h2><p>This source record contains 577 numeric observations. The source distinguishes 577 model identities or configurations. A model may appear more than once; check the version, tools and run budget before comparing. <a data-nav href=\"/benchmarks/artificial-analysis-humanitys-last-exam?lang=en&amp;tab=results\">Read results and row-level evidence →</a></p><dl><div class=\"fact\"><dt>Metric direction</dt><dd>higher is better</dd></div></dl><h3>Start with these resources</h3><ul><li><a href=\"https://artificialanalysis.ai/evaluations/humanitys-last-exam\">Catalog source</a> <span class=\"result-meta\">· artificialanalysis.ai</span></li></ul><details><summary>Cited documents and dates (1)</summary><ul><li><a href=\"https://artificialanalysis.ai/evaluations/humanitys-last-exam\">Humanity’s Last Exam</a></li></ul></details><p class=\"evidence-note\">Catalog collected on 2026-08-25; resources and fields reflect that saved source.</p></section>","zh":"<section class=\"publication-sources prose\"><h2>原始发布</h2><p>本条 Artificial Analysis 记录对应的原始 Humanity’s Last Exam 发布资料。成绩仍为独立采集的 2026 年 8 月 25 日 Artificial Analysis 快照；论文与数据集的后续修订不能证明每条历史评测的具体配置。</p><p class=\"evidence-note\">核对于 2026-10-29</p><ul><li><a href=\"https://lastexam.ai/\">官方项目 · Humanity’s Last Exam · original project</a></li><li><a href=\"https://arxiv.org/abs/2501.14249\">原论文 · Humanity’s Last Exam · original paper and version history</a></li><li><a href=\"https://huggingface.co/datasets/cais/hle\">官方数据集 · Humanity’s Last Exam · official dataset</a></li><li><a href=\"https://github.com/centerforaisafety/hle\">官方仓库 · Humanity’s Last Exam · official evaluation repository</a></li></ul></section><section class=\"record-evidence prose\"><h2>已收录的评测资料</h2><p>这条来源记录收录了 577 条数值成绩。来源区分了 577 个模型身份或配置。同一模型可能有多条记录；比较前请核对具体版本、工具和运行预算。 <a data-nav href=\"/benchmarks/artificial-analysis-humanitys-last-exam?lang=zh&amp;tab=results\">查看成绩及逐条证据 →</a></p><dl><div class=\"fact\"><dt>指标方向</dt><dd>数值越高越好</dd></div></dl><h3>从这些资料开始</h3><ul><li><a href=\"https://artificialanalysis.ai/evaluations/humanitys-last-exam\">收录来源</a> <span class=\"result-meta\">· artificialanalysis.ai</span></li></ul><details><summary>引用文档及日期（1）</summary><ul><li><a href=\"https://artificialanalysis.ai/evaluations/humanitys-last-exam\">Humanity’s Last Exam</a></li></ul></details><p class=\"evidence-note\">目录采集于 2026-08-25，资料入口与字段反映当时保存的来源。</p></section>"},"topic_definitions":[{"group":"capability","id":"coding","label":{"en":"Coding","zh":"编程"}},{"group":"capability","id":"computer-use","label":{"en":"Computer Use","zh":"电脑操作"}},{"group":"capability","id":"agents","label":{"en":"Tools & Agents","zh":"工具与智能体"}},{"group":"capability","id":"multimodal","label":{"en":"Multimodal","zh":"多模态"}},{"group":"capability","id":"reasoning-math","label":{"en":"Reasoning & Math","zh":"推理与数学"}},{"group":"capability","id":"long-context","label":{"en":"Long Context","zh":"长上下文"}},{"group":"capability","id":"language","label":{"en":"Language","zh":"语言"}},{"group":"capability","id":"safety","label":{"en":"Safety","zh":"安全与可靠性"}},{"group":"domain","id":"cybersecurity","label":{"en":"Cybersecurity","zh":"网络安全"}},{"group":"domain","id":"finance","label":{"en":"Finance","zh":"金融"}},{"group":"domain","id":"medical","label":{"en":"Medical","zh":"医疗"}},{"group":"domain","id":"science","label":{"en":"Science","zh":"科学"}}],"siblings":[],"related_records":[{"slug":"artificial-analysis-aa-omniscience-non-hallucination","name":"AA-Omniscience Non-Hallucination Rate","basis":"shared_category"},{"slug":"artificial-analysis-aa-omniscience-accuracy","name":"AA-Omniscience Accuracy","basis":"shared_category"},{"slug":"artificial-analysis-critpt","name":"CritPt","basis":"shared_category"},{"slug":"artificial-analysis-aa-lcr","name":"AA-LCR","basis":"shared_category"},{"slug":"artificial-analysis-gpqa-diamond","name":"GPQA Diamond","basis":"shared_category"},{"slug":"artificial-analysis-scicode","name":"SciCode","basis":"shared_category"},{"slug":"artificial-analysis-tau3-banking","name":"τ³-Banking","basis":"shared_category"},{"slug":"artificial-analysis-gdpval-aa-v2-raw-elo","name":"GDPval-AA v2 (Elo)","basis":"shared_category"}],"attention_signals":null}}
